{"id":"https://openalex.org/W2117904145","doi":"https://doi.org/10.1093/bioinformatics/btp043","title":"Variable locus length in the human genome leads to ascertainment bias in functional inference for non-coding elements","display_name":"Variable locus length in the human genome leads to ascertainment bias in functional inference for non-coding elements","publication_year":2009,"publication_date":"2009-01-25","ids":{"openalex":"https://openalex.org/W2117904145","doi":"https://doi.org/10.1093/bioinformatics/btp043","mag":"2117904145","pmid":"https://pubmed.ncbi.nlm.nih.gov/19168912"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btp043","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp043","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/25/5/578/16892205/btp043.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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/25/5/578/16892205/btp043.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053257775","display_name":"Leila Taher","orcid":"https://orcid.org/0000-0002-2013-5426"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leila Taher","raw_affiliation_strings":["Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071763912","display_name":"Ivan Ovcharenko","orcid":"https://orcid.org/0000-0002-9730-7732"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ivan Ovcharenko","raw_affiliation_strings":["Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071763912"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.3279,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.88427052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"25","issue":"5","first_page":"578","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.383899986743927,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.383899986743927,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.25279998779296875,"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/T10885","display_name":"Gene expression and cancer classification","score":0.13699999451637268,"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/annotation","display_name":"Annotation","score":0.6387100219726562},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.6208726167678833},{"id":"https://openalex.org/keywords/locus","display_name":"Locus (genetics)","score":0.6191369295120239},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.598922848701477},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5751513838768005},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.564960777759552},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.547859787940979},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5405759811401367},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5008049011230469},{"id":"https://openalex.org/keywords/gene-annotation","display_name":"Gene Annotation","score":0.4257390797138214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.35129520297050476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19089528918266296}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6387100219726562},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.6208726167678833},{"id":"https://openalex.org/C84597430","wikidata":"https://www.wikidata.org/wiki/Q106227","display_name":"Locus (genetics)","level":3,"score":0.6191369295120239},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.598922848701477},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5751513838768005},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.564960777759552},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.547859787940979},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5405759811401367},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5008049011230469},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.4257390797138214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35129520297050476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19089528918266296}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D021901","descriptor_name":"DNA, Intergenic","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D021901","descriptor_name":"DNA, Intergenic","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D021901","descriptor_name":"DNA, Intergenic","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btp043","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp043","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/25/5/578/16892205/btp043.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19168912","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19168912","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:2647827","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2647827","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btp043","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp043","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/25/5/578/16892205/btp043.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328486","display_name":"Narodowy Instytut Lek\u00f3w","ror":"https://ror.org/05m2pwn60"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1531954825","https://openalex.org/W1587004646","https://openalex.org/W1600524753","https://openalex.org/W1901437611","https://openalex.org/W1996760543","https://openalex.org/W1998261914","https://openalex.org/W2057829817","https://openalex.org/W2061127877","https://openalex.org/W2081831722","https://openalex.org/W2082607144","https://openalex.org/W2096003410","https://openalex.org/W2096349367","https://openalex.org/W2100990361","https://openalex.org/W2102636283","https://openalex.org/W2102992354","https://openalex.org/W2103017472","https://openalex.org/W2107903949","https://openalex.org/W2113142309","https://openalex.org/W2114865095","https://openalex.org/W2116251070","https://openalex.org/W2119412782","https://openalex.org/W2123060905","https://openalex.org/W2124388496","https://openalex.org/W2125539728","https://openalex.org/W2130962401","https://openalex.org/W2130988208","https://openalex.org/W2140628921","https://openalex.org/W2143228020","https://openalex.org/W2145144631","https://openalex.org/W2145673003","https://openalex.org/W2147449602","https://openalex.org/W2151464048","https://openalex.org/W2165674132","https://openalex.org/W2166574880","https://openalex.org/W2168783124","https://openalex.org/W2171030481","https://openalex.org/W2606759007","https://openalex.org/W4248234957","https://openalex.org/W4405648826","https://openalex.org/W6649604308","https://openalex.org/W6677537331","https://openalex.org/W6736732120"],"related_works":["https://openalex.org/W2059565715","https://openalex.org/W2901823680","https://openalex.org/W2009940763","https://openalex.org/W4361192415","https://openalex.org/W2126804125","https://openalex.org/W2946410450","https://openalex.org/W2162782320","https://openalex.org/W2137318037","https://openalex.org/W4386637333","https://openalex.org/W1760213857"],"abstract_inverted_index":{"MOTIVATION:":[0],"Several":[1],"functional":[2,129,181,231],"gene":[3,23,56,187,245],"annotation":[4,89,130,188,246],"databases":[5,189],"have":[6,65],"been":[7],"developed":[8],"in":[9,58,101,213],"the":[10,19,27,42,48,59,78,88,98,109,119,128,132,202,205,211,214,217,226,230],"recent":[11],"years,":[12],"and":[13,32,62,122,160,223],"are":[14,84,93],"widely":[15],"used":[16],"to":[17,41,140,165,242],"infer":[18],"biological":[20],"function":[21,79,125],"of":[22,44,69,80,90,131,150,198,204,216,233],"sets,":[24],"by":[25,73,113],"scrutinizing":[26],"attributes":[28],"that":[29,83,180,208],"appear":[30],"over-":[31,143],"underrepresented.":[33],"However,":[34],"this":[35],"strategy":[36],"is":[37,138],"not":[38],"directly":[39],"applicable":[40],"study":[43],"non-coding":[45,49,81,116,184,218,234],"DNA,":[46],"as":[47,154,172],"sequence":[50],"span":[51],"varies":[52],"greatly":[53],"among":[54],"different":[55,221],"loci":[57,64,222],"human":[60,120],"genome":[61,121],"longer":[63],"a":[66,147,191,196],"higher":[67],"likelihood":[68],"being":[70],"selected":[71],"purely":[72],"chance.":[74],"Therefore,":[75],"conclusions":[76],"involving":[77],"elements":[82,117,185],"drawn":[85],"based":[86,126],"on":[87,127],"neighboring":[91],"genes":[92],"often":[94],"biased.":[95],"We":[96,194],"assessed":[97],"systematic":[99],"bias":[100,228],"several":[102],"particular":[103],"Gene":[104],"Ontology":[105],"(GO)":[106],"categories":[107,152,207],"using":[108,186],"standard":[110],"hypergeometric":[111],"test,":[112],"randomly":[114],"sampling":[115],"from":[118,229],"inferring":[123],"their":[124],"closest":[133],"genes.":[134],"While":[135],"no":[136],"category":[137],"expected":[139],"occur":[141],"significantly":[142],"or":[144],"underrepresented":[145],"for":[146,183,201,210],"random":[148],"selection":[149],"elements,":[151],"such":[153,171],"'cell":[155],"adhesion',":[156],"'nervous":[157],"system":[158],"development'":[159],"'transcription":[161],"factor":[162],"activities'":[163],"appeared":[164],"be":[166,239],"systematically":[167],"overrepresented,":[168],"while":[169],"others":[170],"'olfactory":[173],"receptor":[174],"activity'-underrepresented.":[175],"RESULTS:":[176],"Our":[177,236],"results":[178],"suggest":[179],"inference":[182],"requires":[190],"special":[192],"correction.":[193],"introduce":[195],"set":[197],"correction":[199],"coefficients":[200],"probabilities":[203],"GO":[206],"accounts":[209],"variability":[212],"length":[215],"DNA":[219],"across":[220],"effectively":[224],"eliminates":[225],"ascertainment":[227],"characterization":[232],"elements.":[235],"approach":[237],"can":[238],"easily":[240],"generalized":[241],"any":[243],"other":[244],"database.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}
