{"id":"https://openalex.org/W2998075929","doi":"https://doi.org/10.1093/bioinformatics/btz952","title":"VEF: a variant filtering tool based on ensemble methods","display_name":"VEF: a variant filtering tool based on ensemble methods","publication_year":2019,"publication_date":"2019-12-19","ids":{"openalex":"https://openalex.org/W2998075929","doi":"https://doi.org/10.1093/bioinformatics/btz952","mag":"2998075929","pmid":"https://pubmed.ncbi.nlm.nih.gov/31873730"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz952","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz952","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073096739","display_name":"Chuanyi Zhang","orcid":"https://orcid.org/0000-0002-6359-0904"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chuanyi Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045294377","display_name":"Idoia Ochoa","orcid":"https://orcid.org/0000-0003-1864-7868"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Idoia Ochoa","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5045294377","https://openalex.org/A5073096739"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.1729,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6428971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"36","issue":"8","first_page":"2328","last_page":"2336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.8399999737739563,"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":0.8399999737739563,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.10140000283718109,"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":0.028699999675154686,"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/computer-science","display_name":"Computer science","score":0.788460373878479},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5177318453788757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5052059292793274},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4819355010986328},{"id":"https://openalex.org/keywords/gold-standard","display_name":"Gold standard (test)","score":0.4705550968647003},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4640779495239258},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.43612852692604065},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43400561809539795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4272611141204834},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08338716626167297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07791945338249207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788460373878479},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5177318453788757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5052059292793274},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4819355010986328},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.4705550968647003},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4640779495239258},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.43612852692604065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43400561809539795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4272611141204834},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08338716626167297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07791945338249207},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","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":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btz952","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz952","pdf_url":null,"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:31873730","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31873730","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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1594031697","https://openalex.org/W1678356000","https://openalex.org/W1988790447","https://openalex.org/W2058401000","https://openalex.org/W2104549677","https://openalex.org/W2108234281","https://openalex.org/W2147733682","https://openalex.org/W2149992227","https://openalex.org/W2168133698","https://openalex.org/W2296597603","https://openalex.org/W2330820318","https://openalex.org/W2487770199","https://openalex.org/W2791837701","https://openalex.org/W2911964244","https://openalex.org/W2951202605","https://openalex.org/W2951331911","https://openalex.org/W2952969776","https://openalex.org/W3098304617","https://openalex.org/W6697520301","https://openalex.org/W6749655863"],"related_works":["https://openalex.org/W2046765700","https://openalex.org/W4384345686","https://openalex.org/W262455470","https://openalex.org/W4242899858","https://openalex.org/W2145834781","https://openalex.org/W2357937784","https://openalex.org/W2547618384","https://openalex.org/W2577782152","https://openalex.org/W2356327704","https://openalex.org/W4240746485"],"abstract_inverted_index":{"MOTIVATION:":[0],"Variants":[1,109],"identified":[2],"by":[3,18],"current":[4],"genomic":[5],"analysis":[6],"pipelines":[7,196],"contain":[8],"many":[9],"incorrectly":[10],"called":[11],"variants.":[12],"These":[13],"can":[14,97],"be":[15,98,208],"potentially":[16],"eliminated":[17],"applying":[19],"state-of-the-art":[20],"filtering":[21,52,75,161,230],"tools,":[22,125],"such":[23],"as":[24,76,126],"Variant":[25],"Quality":[26],"Score":[27],"Recalibration":[28],"(VQSR)":[29],"or":[30],"Hard":[31],"Filtering":[32],"(HF).":[33],"However,":[34],"these":[35,71,156],"methods":[36,59],"are":[37,151,200,253],"very":[38],"user-dependent":[39],"and":[40,67,117,167,187,193,244],"fail":[41],"to":[42,70,101,207],"run":[43],"in":[44,106,191,217],"some":[45,179],"cases.":[46],"We":[47,153],"propose":[48],"VEF,":[49],"a":[50,77,107,214,236],"variant":[51,82],"tool":[53,162],"based":[54],"on":[55,155],"decision":[56],"tree":[57],"ensemble":[58],"that":[60,158,173],"overcomes":[61],"the":[62,103,123,136,148,159,185,204,231],"main":[63],"drawbacks":[64],"of":[65,235],"VQSR":[66,166,223],"HF.":[68,168],"Contrary":[69],"methods,":[72],"we":[73,127,138,171],"treat":[74],"supervised":[78],"learning":[79],"problem,":[80],"using":[81],"call":[83],"data":[84,157,252],"with":[85,122,222],"known":[86],"'true'":[87],"variants,":[88],"i.e.":[89],"gold":[90,149],"standard,":[91],"for":[92,146,229],"training.":[93],"Once":[94],"trained,":[95],"VEF":[96,163,174],"directly":[99],"applied":[100],"filter":[102],"variants":[104],"contained":[105],"given":[108],"Call":[110],"Format":[111],"(VCF)":[112],"file":[113],"(we":[114],"consider":[115],"training":[116,186,205],"testing":[118,188],"VCF":[119],"files":[120],"generated":[121],"same":[124],"assume":[128],"they":[129],"will":[130],"share":[131],"feature":[132],"characteristics).":[133],"RESULTS:":[134],"For":[135],"analysis,":[137],"used":[139],"whole":[140],"genome":[141],"sequencing":[142,195],"(WGS)":[143],"Human":[144,238],"datasets":[145,189],"which":[147],"standards":[150],"available.":[152],"show":[154,172],"proposed":[160],"consistently":[164],"outperforms":[165],"In":[169],"addition,":[170],"generalizes":[175],"well":[176],"even":[177],"when":[178,184,194,220],"features":[180],"have":[181],"missing":[182],"values,":[183],"differ":[190],"coverage,":[192],"other":[197],"than":[198],"GATK":[199],"used.":[201],"Finally,":[202],"since":[203],"needs":[206],"performed":[209],"only":[210],"once,":[211],"there":[212],"is":[213],"significant":[215],"saving":[216],"running":[218],"time":[219],"compared":[221],"(4":[224],"versus":[225],"50":[226],"min":[227],"approximately":[228],"single":[232],"nucleotide":[233],"polymorphisms":[234],"WGS":[237],"sample).":[239],"AVAILABILITY":[240],"AND":[241],"IMPLEMENTATION:":[242],"Code":[243],"scripts":[245],"available":[246,254],"at:":[247],"github.com/ChuanyiZ/vef.":[248],"SUPPLEMENTARY":[249],"INFORMATION:":[250],"Supplementary":[251],"at":[255],"Bioinformatics":[256],"online.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}