{"id":"https://openalex.org/W2121306329","doi":"https://doi.org/10.1093/bioinformatics/bth120","title":"Gap statistics for whole genome shotgun DNA sequencing projects","display_name":"Gap statistics for whole genome shotgun DNA sequencing projects","publication_year":2004,"publication_date":"2004-02-19","ids":{"openalex":"https://openalex.org/W2121306329","doi":"https://doi.org/10.1093/bioinformatics/bth120","mag":"2121306329","pmid":"https://pubmed.ncbi.nlm.nih.gov/14962917"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth120","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth120","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/10/1527/650362/bth120.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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/20/10/1527/650362/bth120.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033154286","display_name":"Michael C. Wendl","orcid":"https://orcid.org/0000-0002-5694-2668"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael C. Wendl","raw_affiliation_strings":["Genome Sequencing Center, Washington University School of Medicine, Box 8501, 4444 Forest Park Blvd., Saint Louis, MO 63108 USA"],"affiliations":[{"raw_affiliation_string":"Genome Sequencing Center, Washington University School of Medicine, Box 8501, 4444 Forest Park Blvd., Saint Louis, MO 63108 USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046565797","display_name":"Shiaw\u2010Pyng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiaw-Pyng Yang","raw_affiliation_strings":["Genome Sequencing Center, Washington University School of Medicine, Box 8501, 4444 Forest Park Blvd., Saint Louis, MO 63108 USA"],"affiliations":[{"raw_affiliation_string":"Genome Sequencing Center, Washington University School of Medicine, Box 8501, 4444 Forest Park Blvd., Saint Louis, MO 63108 USA","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033154286"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.7235,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.68445601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"20","issue":"10","first_page":"1527","last_page":"1534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","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/T10015","display_name":"Genomics and Phylogenetic Studies","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/T10521","display_name":"RNA and protein synthesis mechanisms","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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/shotgun-sequencing","display_name":"Shotgun sequencing","score":0.7221463918685913},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6704413890838623},{"id":"https://openalex.org/keywords/shotgun","display_name":"Shotgun","score":0.5031766295433044},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.49136629700660706},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4668826162815094},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4419858157634735},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4311383366584778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41978150606155396},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4110792577266693},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41025134921073914},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.36118388175964355},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.31980061531066895},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26941028237342834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1645156741142273},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15042999386787415}],"concepts":[{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.7221463918685913},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6704413890838623},{"id":"https://openalex.org/C2781434637","wikidata":"https://www.wikidata.org/wiki/Q486396","display_name":"Shotgun","level":3,"score":0.5031766295433044},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.49136629700660706},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4668826162815094},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4419858157634735},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4311383366584778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41978150606155396},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4110792577266693},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41025134921073914},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36118388175964355},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.31980061531066895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26941028237342834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1645156741142273},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15042999386787415},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bth120","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth120","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/10/1527/650362/bth120.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:14962917","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14962917","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:CiteSeerX.psu:10.1.1.630.6432","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.630.6432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/20/10/1527.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bth120","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth120","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/10/1527/650362/bth120.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2121306329.pdf","grobid_xml":"https://content.openalex.org/works/W2121306329.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1528679632","https://openalex.org/W1608218663","https://openalex.org/W1635391495","https://openalex.org/W1636627834","https://openalex.org/W1926303070","https://openalex.org/W1966711026","https://openalex.org/W1979186179","https://openalex.org/W1992404301","https://openalex.org/W1992537250","https://openalex.org/W1992950355","https://openalex.org/W1996231070","https://openalex.org/W2010578391","https://openalex.org/W2040048905","https://openalex.org/W2050923959","https://openalex.org/W2054468433","https://openalex.org/W2070407853","https://openalex.org/W2087750699","https://openalex.org/W2100641815","https://openalex.org/W2108360478","https://openalex.org/W2113679691","https://openalex.org/W2117936709","https://openalex.org/W2121016876","https://openalex.org/W2124259172","https://openalex.org/W2125196454","https://openalex.org/W2127230663","https://openalex.org/W2129873761","https://openalex.org/W2129895984","https://openalex.org/W2141217788","https://openalex.org/W2141652419","https://openalex.org/W2142103600","https://openalex.org/W2144662851","https://openalex.org/W2148072340","https://openalex.org/W2149731513","https://openalex.org/W2151464048","https://openalex.org/W2156622081","https://openalex.org/W2158355883","https://openalex.org/W2161668137","https://openalex.org/W2167493116","https://openalex.org/W2168393617","https://openalex.org/W2168909179","https://openalex.org/W2170258388","https://openalex.org/W2752932982","https://openalex.org/W4231413018","https://openalex.org/W4391044213"],"related_works":["https://openalex.org/W4210312276","https://openalex.org/W2417514914","https://openalex.org/W1641084016","https://openalex.org/W2018832993","https://openalex.org/W4255415692","https://openalex.org/W3128701120","https://openalex.org/W2994945316","https://openalex.org/W4253705341","https://openalex.org/W4386668515","https://openalex.org/W4236337243"],"abstract_inverted_index":{"Using":[0],"a":[1,22,95,118],"statistical":[2],"scaling":[3],"factor":[4],"and":[5,79],"data":[6],"from":[7,65],"20":[8],"representative":[9],"whole":[10],"genome":[11],"shotgun":[12],"projects,":[13],"we":[14],"construct":[15],"regression":[16],"equations":[17],"that":[18,55,63,109,121],"relate":[19],"coverage":[20,80,111],"to":[21,31,71],"normalized":[23],"gap":[24,104],"measure.":[25],"Prokaryotic":[26],"genomes":[27],"do":[28],"not":[29,123],"correlate":[30],"sequence":[32],"coverage,":[33],"while":[34],"eukaryotes":[35],"show":[36],"strong":[37],"correlation":[38],"if":[39],"the":[40,101,126],"chaff":[41],"is":[42,117],"ignored.":[43],"Gaps":[44],"decrease":[45],"at":[46],"an":[47],"exponential":[48],"rate":[49],"of":[50,54,103],"only":[51],"about":[52],"one-third":[53],"predicted":[56],"via":[57],"theory":[58,66],"alone.":[59],"Case":[60],"studies":[61,116],"suggest":[62],"departure":[64],"can":[67],"largely":[68],"be":[69,92],"attributed":[70],"assembly":[72],"difficulties":[73],"for":[74,125],"repeat-rich":[75],"genomes,":[76],"but":[77],"bias":[78],"anomalies":[81],"are":[82,87],"also":[83,107],"important":[84],"when":[85],"repeats":[86],"sparse.":[88],"Such":[89],"factors":[90],"cannot":[91],"readily":[93],"characterized":[94],"priori,":[96],"suggesting":[97],"upper":[98],"limits":[99],"on":[100],"accuracy":[102],"prediction.":[105],"We":[106],"find":[108],"diminishing":[110],"probability":[112],"discussed":[113],"in":[114],"other":[115],"theoretical":[119],"artifact":[120],"does":[122],"arise":[124],"typical":[127],"project.":[128]},"counts_by_year":[{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
