{"id":"https://openalex.org/W2567598959","doi":"https://doi.org/10.1093/bioinformatics/btw748","title":"Improved VCF normalization for accurate VCF comparison","display_name":"Improved VCF normalization for accurate VCF comparison","publication_year":2016,"publication_date":"2016-11-23","ids":{"openalex":"https://openalex.org/W2567598959","doi":"https://doi.org/10.1093/bioinformatics/btw748","mag":"2567598959","pmid":"https://pubmed.ncbi.nlm.nih.gov/27993787"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btw748","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw748","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/7/964/25149813/btw748.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/33/7/964/25149813/btw748.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056018277","display_name":"Arash Bayat","orcid":"https://orcid.org/0000-0002-8799-7776"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Arash Bayat","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080061732","display_name":"Bruno Ga\u00ebta","orcid":"https://orcid.org/0000-0003-4723-4982"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bruno Ga\u00ebta","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079126989","display_name":"Aleksandar Ignjatovi\u0107","orcid":"https://orcid.org/0000-0001-7427-4934"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aleksandar Ignjatovic","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030042327","display_name":"Sri Parameswaran","orcid":"https://orcid.org/0000-0003-0435-9080"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sri Parameswaran","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056018277"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.4813,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86049392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"7","first_page":"964","last_page":"970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.4959000051021576,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.4959000051021576,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.430400013923645,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.040800001472234726,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/computer-science","display_name":"Computer science","score":0.7105516195297241},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5940433144569397},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5249882936477661},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4736807644367218},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.467013418674469},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.440122127532959},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.32782378792762756},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.14658859372138977},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11860820651054382},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10090678930282593},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09093844890594482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7105516195297241},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5940433144569397},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5249882936477661},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4736807644367218},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.467013418674469},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.440122127532959},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.32782378792762756},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14658859372138977},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11860820651054382},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10090678930282593},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09093844890594482},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000483","descriptor_name":"Alleles","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000483","descriptor_name":"Alleles","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000483","descriptor_name":"Alleles","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btw748","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw748","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/7/964/25149813/btw748.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:27993787","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27993787","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btw748","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw748","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/7/964/25149813/btw748.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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1919257374","https://openalex.org/W2050109119","https://openalex.org/W2095680943","https://openalex.org/W2095763520","https://openalex.org/W2103441770","https://openalex.org/W2104549677","https://openalex.org/W2104816742","https://openalex.org/W2107282968","https://openalex.org/W2108234281","https://openalex.org/W2108996658","https://openalex.org/W2124465358","https://openalex.org/W2149992227","https://openalex.org/W2152143598","https://openalex.org/W2157539385","https://openalex.org/W2168133698","https://openalex.org/W2189510244","https://openalex.org/W2950919185","https://openalex.org/W6675468382","https://openalex.org/W6675787119","https://openalex.org/W6676286517","https://openalex.org/W6683495024"],"related_works":["https://openalex.org/W2921363728","https://openalex.org/W2279684808","https://openalex.org/W3137911940","https://openalex.org/W3217304749","https://openalex.org/W2894932706","https://openalex.org/W2066142713","https://openalex.org/W2767606877","https://openalex.org/W2582968398","https://openalex.org/W4223446368","https://openalex.org/W4232517363"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,191],"Variant":[2,15],"Call":[3],"Format":[4],"(VCF)":[5],"is":[6,46,69,86,156],"widely":[7],"used":[8],"to":[9,48,127,131,157],"store":[10],"data":[11,210],"about":[12],"genetic":[13],"variation.":[14],"calling":[16],"workflows":[17],"detect":[18],"potential":[19],"variants":[20,140],"in":[21,35,81,91,112,123,178],"large":[22],"numbers":[23],"of":[24,42,63,154,165,184],"short":[25],"sequence":[26],"reads":[27],"generated":[28],"by":[29,95,141],"DNA":[30],"sequencing":[31],"and":[32,85,136],"report":[33],"them":[34],"VCF":[36,56,67,102,115,125,166,186],"format.":[37],"To":[38],"evaluate":[39],"the":[40,121,128,139,148,152,163,175,182],"accuracy":[41],"variant":[43,77],"callers,":[44],"it":[45],"critical":[47],"correctly":[49],"compare":[50],"their":[51],"output":[52],"against":[53],"a":[54,59,70,92,101,124,133,170],"reference":[55,129,149],"file":[57,116,126],"containing":[58],"gold":[60],"standard":[61],"set":[62],"variants.":[64],"However,":[65],"comparing":[66],"files":[68],"complicated":[71],"task":[72],"as":[73,174],"an":[74,159],"individual":[75],"genomic":[76],"can":[78],"be":[79],"represented":[80],"several":[82],"different":[83,96,185],"ways":[84],"therefore":[87],"not":[88],"necessarily":[89],"reported":[90],"unique":[93],"way":[94],"software.":[97],"RESULTS:":[98],"We":[99],"introduce":[100],"normalization":[103,172],"method":[104,173],"called":[105],"Best":[106],"Alignment":[107],"Normalisation":[108],"(BAN)":[109],"that":[110],"results":[111],"more":[113],"accurate":[114,160],"comparison.":[117],"BAN":[118,155,192],"applies":[119],"all":[120],"variations":[122],"genome":[130,145],"create":[132],"sample":[134,144],"genome,":[135],"then":[137],"recalls":[138],"aligning":[142],"this":[143],"back":[146],"with":[147,197],"genome.":[150],"Since":[151],"purpose":[153],"get":[158],"result":[161],"at":[162,213],"time":[164],"comparison,":[167],"we":[168],"define":[169],"better":[171],"one":[176],"resulting":[177],"less":[179],"disagreement":[180],"between":[181],"outputs":[183],"comparators.":[187],"AVAILABILITY":[188],"AND":[189],"IMPLEMENTATION:":[190],"Linux":[193],"bash":[194],"script":[195],"along":[196],"required":[198],"software":[199],"are":[200,211],"publicly":[201],"available":[202,212],"on":[203],"https://sites.google.com/site/banadf16.":[204],"CONTACT:":[205],"A.Bayat@unsw.edu.au.":[206],"SUPPLEMENTARY":[207],"INFORMATION:":[208],"Supplementary":[209],"Bioinformatics":[214],"online.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-23T13:55:30.953635","created_date":"2025-10-10T00:00:00"}
