{"id":"https://openalex.org/W4220999544","doi":"https://doi.org/10.1371/journal.pcbi.1009939","title":"Transcriptome diversity is a systematic source of variation in RNA-sequencing data","display_name":"Transcriptome diversity is a systematic source of variation in RNA-sequencing data","publication_year":2022,"publication_date":"2022-03-24","ids":{"openalex":"https://openalex.org/W4220999544","doi":"https://doi.org/10.1371/journal.pcbi.1009939","pmid":"https://pubmed.ncbi.nlm.nih.gov/35324895"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1009939","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009939","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.1009939","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037909523","display_name":"Pablo E. Garc\u00eda-Nieto","orcid":"https://orcid.org/0000-0001-8696-0923"},"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":"Pablo E. Garc\u00eda-Nieto","raw_affiliation_strings":["Department of Biology, Stanford University, Stanford, California, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, Stanford University, Stanford, California, United States of America","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102912836","display_name":"Ban Wang","orcid":"https://orcid.org/0000-0003-2907-6132"},"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":"Ban Wang","raw_affiliation_strings":["Department of Biology, Stanford University, Stanford, California, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2907-6132","affiliations":[{"raw_affiliation_string":"Department of Biology, Stanford University, Stanford, California, United States of America","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088684784","display_name":"Hunter B. Fraser","orcid":"https://orcid.org/0000-0001-8400-8541"},"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":true,"raw_author_name":"Hunter B. Fraser","raw_affiliation_strings":["Department of Biology, Stanford University, Stanford, California, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, Stanford University, Stanford, California, United States of America","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088684784"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":1.7359,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.84440461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"18","issue":"3","first_page":"e1009939","last_page":"e1009939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9973000288009644,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9973000288009644,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.9941999912261963,"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/transcriptome","display_name":"Transcriptome","score":0.7369897365570068},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.633324146270752},{"id":"https://openalex.org/keywords/rna-seq","display_name":"RNA-Seq","score":0.6083607077598572},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5582321882247925},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.43591347336769104},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4221428632736206},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.41934719681739807},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.41832488775253296},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4107184410095215},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.3786814510822296},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.3329505920410156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2957131266593933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13607889413833618}],"concepts":[{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.7369897365570068},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.633324146270752},{"id":"https://openalex.org/C107397762","wikidata":"https://www.wikidata.org/wiki/Q2542347","display_name":"RNA-Seq","level":5,"score":0.6083607077598572},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5582321882247925},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.43591347336769104},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4221428632736206},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.41934719681739807},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.41832488775253296},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4107184410095215},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.3786814510822296},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3329505920410156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2957131266593933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13607889413833618},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":"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":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"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":"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":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1371/journal.pcbi.1009939","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009939","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:35324895","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35324895","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":null},{"id":"pmh:oai:RePEc:plo:pcbi00:1009939","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1009939","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:169983e041c144fea4ce3b0cc481ba73","is_oa":true,"landing_page_url":"https://doaj.org/article/169983e041c144fea4ce3b0cc481ba73","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 18, Iss 3, p e1009939 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8982896","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8982896","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":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1009939","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1009939","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/G434587623","display_name":null,"funder_award_id":"2R01GM097171-09","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1970156673","https://openalex.org/W1986911601","https://openalex.org/W1995875735","https://openalex.org/W1997494129","https://openalex.org/W2018838463","https://openalex.org/W2049422258","https://openalex.org/W2055027171","https://openalex.org/W2107018762","https://openalex.org/W2130116522","https://openalex.org/W2152239989","https://openalex.org/W2159170638","https://openalex.org/W2168342464","https://openalex.org/W2236822143","https://openalex.org/W2529971605","https://openalex.org/W2536902964","https://openalex.org/W2586476886","https://openalex.org/W2606715885","https://openalex.org/W2607211817","https://openalex.org/W2801400022","https://openalex.org/W2949960840","https://openalex.org/W2951158909","https://openalex.org/W2963367647","https://openalex.org/W2974147992","https://openalex.org/W2974676489","https://openalex.org/W3004940273","https://openalex.org/W3006025691","https://openalex.org/W3133859624","https://openalex.org/W6689944646"],"related_works":["https://openalex.org/W4394359997","https://openalex.org/W4362511652","https://openalex.org/W4362511917","https://openalex.org/W4362511922","https://openalex.org/W4362485688","https://openalex.org/W4362530184","https://openalex.org/W4362530193","https://openalex.org/W2904597490","https://openalex.org/W4362485661","https://openalex.org/W4394365953"],"abstract_inverted_index":{"RNA":[0],"sequencing":[1,45],"has":[2,69,80,124],"been":[3,18,48,70],"widely":[4],"used":[5,71],"as":[6,40],"an":[7],"essential":[8],"tool":[9],"to":[10,20,28,50,72,83],"probe":[11],"gene":[12,66,106,154],"expression.":[13],"While":[14],"standard":[15],"practices":[16],"have":[17,47],"established":[19],"analyze":[21],"RNA-seq":[22],"data,":[23],"it":[24,79],"is":[25,109],"still":[26],"challenging":[27,82],"interpret":[29,84],"and":[30,36,44,108,130,136,157],"remove":[31],"artifactual":[32],"signals.":[33],"Several":[34],"biological":[35,131],"technical":[37,129],"factors":[38],"such":[39],"sex,":[41],"age,":[42],"batches,":[43],"technology":[46],"found":[49],"bias":[51],"these":[52,85],"estimates.":[53],"Probabilistic":[54],"estimation":[55],"of":[56,103,150],"expression":[57,67,107,155],"residuals":[58],"(PEER),":[59],"which":[60],"infers":[61],"broad":[62],"variance":[63],"components":[64],"in":[65,105,115,152],"measurements,":[68],"account":[73],"for":[74,146],"some":[75],"systematic":[76],"effects,":[77],"but":[78],"remained":[81],"PEER":[86,116,158],"factors.":[87,117],"Here":[88],"we":[89],"show":[90,120],"that":[91,121],"transcriptome":[92,122,140],"diversity-a":[93],"simple":[94,144],"metric":[95],"based":[96],"on":[97],"Shannon":[98],"entropy-explains":[99],"a":[100,143,147],"large":[101],"portion":[102],"variability":[104],"the":[110],"strongest":[111],"known":[112],"factor":[113],"encoded":[114],"We":[118],"then":[119],"diversity":[123,141],"significant":[125],"associations":[126],"with":[127],"multiple":[128],"variables":[132],"across":[133],"diverse":[134],"organisms":[135],"datasets.":[137],"In":[138],"sum,":[139],"provides":[142],"explanation":[145],"major":[148],"source":[149],"variation":[151],"both":[153],"estimates":[156],"covariates.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
