{"id":"https://openalex.org/W2950213774","doi":"https://doi.org/10.1093/bioinformatics/btw797","title":"VarMatch: robust matching of small variant datasets using flexible scoring schemes","display_name":"VarMatch: robust matching of small variant datasets using flexible scoring schemes","publication_year":2016,"publication_date":"2016-12-13","ids":{"openalex":"https://openalex.org/W2950213774","doi":"https://doi.org/10.1093/bioinformatics/btw797","mag":"2950213774","pmid":"https://pubmed.ncbi.nlm.nih.gov/28011786"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btw797","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw797","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/9/1301/25151252/btw797.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/33/9/1301/25151252/btw797.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100722234","display_name":"Chen Sun","orcid":"https://orcid.org/0000-0001-8772-9627"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Sun","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, The Pennsylvania State University, State College, PA, USA","Department of Computer Science and Engineering, The Pennsylvania State University, State College, PA, USA","Genome Sciences Institute at the Huck, The Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Genome Sciences Institute at the Huck, The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066909672"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.2849,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.923252,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"33","issue":"9","first_page":"1301","last_page":"1308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.6674000024795532,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.6674000024795532,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.1281999945640564,"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/T11719","display_name":"Data Quality and Management","score":0.03269999846816063,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7699785232543945},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6611844897270203},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.657946765422821},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5579861998558044},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5397696495056152},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49070489406585693},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46345943212509155},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42547863721847534},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35992950201034546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14539018273353577},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07122454047203064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699785232543945},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6611844897270203},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.657946765422821},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5579861998558044},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5397696495056152},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49070489406585693},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46345943212509155},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42547863721847534},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35992950201034546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14539018273353577},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07122454047203064},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","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":"D000465","descriptor_name":"Algorithms","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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"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":"D017422","descriptor_name":"Sequence Analysis, DNA","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},{"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/btw797","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw797","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/9/1301/25151252/btw797.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:28011786","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28011786","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/btw797","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw797","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/9/1301/25151252/btw797.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":[{"id":"https://openalex.org/G2039187732","display_name":"ABI Innovation: A Novel Framework for Detecting Genomic Structural Variation","funder_award_id":"1356529","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3426846984","display_name":"III: Small: Reconstructing viral population without using a reference genome","funder_award_id":"1421908","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3926047959","display_name":"XPS: FULL: DSD: End-to-end Acceleration of Genomic Workflows on Emerging Heterogeneous Supercomputers","funder_award_id":"1439057","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4106800444","display_name":"CAREER: De Novo Assembly of Large Genomic Data","funder_award_id":"1453527","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950213774.pdf","grobid_xml":"https://content.openalex.org/works/W2950213774.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2007325090","https://openalex.org/W2030295903","https://openalex.org/W2033173420","https://openalex.org/W2052664297","https://openalex.org/W2060965924","https://openalex.org/W2076359272","https://openalex.org/W2095763520","https://openalex.org/W2096791516","https://openalex.org/W2103811075","https://openalex.org/W2108234281","https://openalex.org/W2108996658","https://openalex.org/W2112691802","https://openalex.org/W2115089273","https://openalex.org/W2119180969","https://openalex.org/W2120748415","https://openalex.org/W2121427560","https://openalex.org/W2140067143","https://openalex.org/W2147733682","https://openalex.org/W2149992227","https://openalex.org/W2155306111","https://openalex.org/W2158336776","https://openalex.org/W2161815151","https://openalex.org/W2168397218","https://openalex.org/W2171777347","https://openalex.org/W2189510244","https://openalex.org/W2190569576","https://openalex.org/W6675787119","https://openalex.org/W6685049644","https://openalex.org/W6687460725","https://openalex.org/W6687645861"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W4321441197","https://openalex.org/W4294432981","https://openalex.org/W4321276295"],"abstract_inverted_index":{"Motivation:":[0],"Small":[1],"variant":[2,83,162],"calling":[3],"is":[4,16,31,59,88,108,117,130,185],"an":[5],"important":[6,17],"component":[7],"of":[8,22,54,67,113],"many":[9,13],"analyses,":[10],"and,":[11],"in":[12,26,120,127],"instances,":[14],"it":[15],"to":[18,51,63,71,97,110,132,160],"determine":[19],"the":[20,65,78,82,99,138,165],"set":[21],"variants":[23,34,115],"which":[24,94],"appear":[25],"multiple":[27,37],"callsets.":[28],"Variant":[29,57],"matching":[30,58,84],"complicated":[32],"by":[33],"that":[35,156,174],"have":[36,44],"equivalent":[38],"representations.":[39,163],"Normalization":[40],"and":[41,116,172,182],"decomposition":[42,141],"algorithms":[43,142],"been":[45],"proposed,":[46],"but":[47],"are":[48,175,198],"not":[49],"robust":[50,109],"different":[52,111,149,161],"representation":[53,112],"complex":[55,114],"variants.":[56,128],"also":[60,147],"usually":[61],"done":[62],"maximize":[64],"number":[66],"matches,":[68],"as":[69,153],"opposed":[70],"other":[72],"optimization":[73,150],"criteria.":[74],"Results:":[75],"We":[76],"present":[77],"VarMatch":[79,107,129,166,184],"algorithm":[80,87],"for":[81,177],"problem.":[85],"Our":[86],"based":[89],"on":[90,143],"a":[91],"theoretical":[92],"result":[93],"allows":[95],"us":[96],"partition":[98],"input":[100],"into":[101],"smaller":[102],"subproblems":[103],"without":[104],"sacrificing":[105],"accuracy.":[106],"particularly":[118],"effective":[119],"low":[121],"complexity":[122],"regions":[123],"or":[124,140,192],"those":[125],"dense":[126],"able":[131],"detect":[133],"more":[134],"matches":[135],"than":[136],"either":[137],"normalization":[139],"tested":[144],"datasets.":[145],"It":[146],"implements":[148],"criteria,":[151],"such":[152],"edit":[154],"distance,":[155],"can":[157],"improve":[158],"robustness":[159],"Finally,":[164],"software":[167],"provides":[168],"summary":[169],"statistics,":[170],"annotations":[171],"visualizations":[173],"useful":[176],"understanding":[178],"callers'":[179],"performance.":[180],"Availability":[181],"Implementation:":[183],"freely":[186],"available":[187,199],"at:":[188],"https://github.com/medvedevgroup/varmatch.":[189],"Contact:":[190],"chensun@cse.psu.edu":[191],"pashadag@cse.psu.edu.":[193],"Supplementary":[194,196],"information:":[195],"data":[197],"at":[200],"Bioinformatics":[201],"online.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
