{"id":"https://openalex.org/W4390046124","doi":"https://doi.org/10.1371/journal.pcbi.1011734","title":"Transcript assembly and annotations: Bias and adjustment","display_name":"Transcript assembly and annotations: Bias and adjustment","publication_year":2023,"publication_date":"2023-12-21","ids":{"openalex":"https://openalex.org/W4390046124","doi":"https://doi.org/10.1371/journal.pcbi.1011734","pmid":"https://pubmed.ncbi.nlm.nih.gov/38127855"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1011734","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1011734","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pcbi.1011734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101815502","display_name":"Qimin Zhang","orcid":"https://orcid.org/0000-0002-5990-1765"},"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":"Qimin Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, Pennsylvania, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5990-1765","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052979637","display_name":"Mingfu Shao","orcid":"https://orcid.org/0000-0001-6112-5139"},"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":"Mingfu Shao","raw_affiliation_strings":["Department of Computer Science and Engineering, School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, Pennsylvania, United States of America","Huck Institutes of the Life Sciences, The Pennsylvania State University, University Park, Pennsylvania, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6112-5139","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University, University Park, Pennsylvania, United States of America","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5052979637"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3043,"currency":"USD","value_usd":3043},"apc_paid":{"value":3043,"currency":"USD","value_usd":3043},"fwci":0.6437,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.65747327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"19","issue":"12","first_page":"e1011734","last_page":"e1011734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9998999834060669,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9998999834060669,"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":0.9997000098228455,"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/T11482","display_name":"RNA modifications and cancer","score":0.9994999766349792,"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/computational-biology","display_name":"Computational biology","score":0.5183021426200867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4010315537452698},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3877890706062317}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5183021426200867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4010315537452698},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3877890706062317}],"mesh":[{"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":"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":"D020033","descriptor_name":"Protein Isoforms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020033","descriptor_name":"Protein Isoforms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020033","descriptor_name":"Protein Isoforms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020033","descriptor_name":"Protein Isoforms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020033","descriptor_name":"Protein Isoforms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020033","descriptor_name":"Protein Isoforms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020033","descriptor_name":"Protein Isoforms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1371/journal.pcbi.1011734","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1011734","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:38127855","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38127855","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":"PLoS computational biology","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10769104","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10769104","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10769104/pdf/pcbi.1011734.pdf","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":"PLoS Comput Biol","raw_type":"Text"},{"id":"pmh:oai:RePEc:plo:pcbi00:1011734","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1011734","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:9affb20fcd454252a08f86d85045e38f","is_oa":true,"landing_page_url":"https://doaj.org/article/9affb20fcd454252a08f86d85045e38f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 19, Iss 12, p e1011734 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1011734","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1011734","pdf_url":null,"source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1219243184","display_name":"Computational Methods for Assembling Multiple RNA-seq Samples","funder_award_id":"5r01hg011065-03","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1877879165","display_name":"CAREER: Algorithms and Tools for Allele-Specific Transcript Assembly","funder_award_id":"2145171","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3280907188","display_name":null,"funder_award_id":"R01HG011065","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G5939242015","display_name":null,"funder_award_id":"DBI-214517","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6827177365","display_name":"BBSRC-NSF/BIO: IIBR Informatics: Collaborative Research: Inference of isoform-level regulatory infrastructures with studies in steroid-producing cells","funder_award_id":"2019797","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/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1482244404","https://openalex.org/W1999574084","https://openalex.org/W2026635277","https://openalex.org/W2042690128","https://openalex.org/W2049126920","https://openalex.org/W2065128082","https://openalex.org/W2066231767","https://openalex.org/W2098680190","https://openalex.org/W2104005232","https://openalex.org/W2114104545","https://openalex.org/W2141458291","https://openalex.org/W2169456326","https://openalex.org/W2173732482","https://openalex.org/W2179438025","https://openalex.org/W2298558585","https://openalex.org/W2323326409","https://openalex.org/W2519019984","https://openalex.org/W2592811885","https://openalex.org/W2768985026","https://openalex.org/W2773298966","https://openalex.org/W2903241977","https://openalex.org/W2964849163","https://openalex.org/W2995527562","https://openalex.org/W3011428862","https://openalex.org/W3022572641","https://openalex.org/W3029661147","https://openalex.org/W3045910546","https://openalex.org/W3111061871","https://openalex.org/W3133859624","https://openalex.org/W3191132797","https://openalex.org/W4210259125","https://openalex.org/W4220754011","https://openalex.org/W4220999759","https://openalex.org/W4224014283","https://openalex.org/W4226305417","https://openalex.org/W4233582454","https://openalex.org/W4306803826","https://openalex.org/W4317553434","https://openalex.org/W4385347606","https://openalex.org/W4399437507"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W2082860237","https://openalex.org/W2119695867","https://openalex.org/W2130076355","https://openalex.org/W1990804418","https://openalex.org/W1993764875","https://openalex.org/W2046158694","https://openalex.org/W2788277189"],"abstract_inverted_index":{"Transcript":[0],"annotations":[1,25,84,102,116,145,157],"play":[2],"a":[3,14,54,175,194,220],"critical":[4],"role":[5],"in":[6],"gene":[7,58],"expression":[8,59],"analysis":[9],"as":[10,13,69,88],"they":[11],"serve":[12],"reference":[15],"for":[16,230],"quantifying":[17],"isoform-level":[18],"expression.":[19],"The":[20],"two":[21],"main":[22],"sources":[23],"of":[24,50,94,100,115,144,168,218],"are":[26,85],"RefSeq":[27],"and":[28,35,83,149,170,173,180,222],"Ensembl/GENCODE,":[29],"but":[30],"discrepancies":[31],"between":[32],"their":[33],"methodologies":[34],"information":[36],"resources":[37],"can":[38,52,126,201],"lead":[39],"to":[40,67,80,90,207,225],"significant":[41,55,176],"differences.":[42],"It":[43],"has":[44],"been":[45],"demonstrated":[46],"that":[47,123,151,200],"the":[48,92,98,113,141,152,160,166,189,216],"choice":[49],"annotation":[51],"have":[53],"impact":[56,114],"on":[57,103,117],"analysis.":[60],"Furthermore,":[61],"transcript":[62,104,118],"assembly":[63,95,105,210],"is":[64,75,106],"closely":[65],"linked":[66],"annotations,":[68,82],"assembling":[70,181,228],"large-scale":[71],"available":[72,197],"RNA-seq":[73],"data":[74],"an":[76,205,209],"effective":[77],"data-driven":[78],"way":[79],"construct":[81],"often":[86],"served":[87],"benchmarks":[89],"evaluate":[91,215],"accuracy":[93],"methods.":[96],"However,":[97],"influence":[99],"different":[101,132,231],"not":[107],"yet":[108],"fully":[109],"understood.":[110],"We":[111,192,214],"investigate":[112],"assembly.":[119],"Surprisingly,":[120],"we":[121,139,164],"observe":[122],"opposite":[124],"conclusions":[125],"arise":[127],"when":[128],"evaluating":[129],"assemblers":[130],"with":[131,183,204],"annotations.":[133],"To":[134],"understand":[135],"this":[136],"striking":[137],"phenomenon,":[138],"compare":[140],"structural":[142,154],"similarity":[143],"at":[146,159,198],"various":[147],"levels":[148],"find":[150],"primary":[153],"difference":[155],"across":[156],"occurs":[158],"intron-chain":[161],"level.":[162],"Next,":[163],"examine":[165],"biotypes":[167],"annotated":[169],"assembled":[171],"transcripts":[172,182],"uncover":[174],"bias":[177],"towards":[178],"annotating":[179],"intron":[184,212],"retentions,":[185],"which":[186],"explains":[187],"above":[188],"contradictory":[190],"conclusions.":[191],"develop":[193],"standalone":[195],"tool,":[196],"https://github.com/Shao-Group/irtool,":[199],"be":[202],"combined":[203],"assembler":[206],"generate":[208],"without":[211],"retentions.":[213],"performance":[217],"such":[219],"pipeline":[221],"offer":[223],"guidance":[224],"select":[226],"appropriate":[227],"tools":[229],"application":[232],"scenarios.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}