{"id":"https://openalex.org/W3047494315","doi":"https://doi.org/10.1093/bioinformatics/btaa628","title":"Seqminer2: an efficient tool to query and retrieve genotypes for statistical genetics analyses from biobank scale sequence dataset","display_name":"Seqminer2: an efficient tool to query and retrieve genotypes for statistical genetics analyses from biobank scale sequence dataset","publication_year":2020,"publication_date":"2020-07-03","ids":{"openalex":"https://openalex.org/W3047494315","doi":"https://doi.org/10.1093/bioinformatics/btaa628","mag":"3047494315","pmid":"https://pubmed.ncbi.nlm.nih.gov/32756942"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa628","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa628","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/19/4951/40418615/btaa628.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/36/19/4951/40418615/btaa628.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101452617","display_name":"Lina Yang","orcid":"https://orcid.org/0000-0001-9130-5122"},"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":"Lina Yang","raw_affiliation_strings":["Department of Public Health Sciences, Penn State College of Medicine , Hershey, PA 17033, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Public Health Sciences, Penn State College of Medicine , Hershey, PA 17033, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076832561","display_name":"Shuang Jiang","orcid":"https://orcid.org/0000-0002-4675-7143"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuang Jiang","raw_affiliation_strings":["Department of Clinical Science, University of Texas Southwestern Medical Center , Dallas, TX 75390, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Clinical Science, University of Texas Southwestern Medical Center , Dallas, TX 75390, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102829129","display_name":"Bibo Jiang","orcid":"https://orcid.org/0000-0002-7985-3780"},"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":"Bibo Jiang","raw_affiliation_strings":["Department of Public Health Sciences, Penn State College of Medicine , Hershey, PA 17033, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Public Health Sciences, Penn State College of Medicine , Hershey, PA 17033, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044571272","display_name":"Dajiang J. Liu","orcid":"https://orcid.org/0000-0001-6553-858X"},"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":"Dajiang J Liu","raw_affiliation_strings":["Department of Public Health Sciences, Penn State College of Medicine , Hershey, PA 17033, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Public Health Sciences, Penn State College of Medicine , Hershey, PA 17033, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100707493","display_name":"Xiaowei Zhan","orcid":"https://orcid.org/0000-0002-6249-7193"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaowei Zhan","raw_affiliation_strings":["Department of Clinical Science, University of Texas Southwestern Medical Center , Dallas, TX 75390, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Clinical Science, University of Texas Southwestern Medical Center , Dallas, TX 75390, USA","institution_ids":["https://openalex.org/I867280407"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044571272","https://openalex.org/A5100707493"],"corresponding_institution_ids":["https://openalex.org/I130769515","https://openalex.org/I867280407"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.07881987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"36","issue":"19","first_page":"4951","last_page":"4954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.8319000005722046,"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":0.8319000005722046,"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":0.04740000143647194,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.0210999995470047,"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/biobank","display_name":"Biobank","score":0.8719680309295654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7504745721817017},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6051023602485657},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5609155893325806},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4794924855232239},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.47429612278938293},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4585355222225189},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.43204864859580994},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41104644536972046},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.24646177887916565},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08579617738723755},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08038723468780518},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07981038093566895}],"concepts":[{"id":"https://openalex.org/C116567970","wikidata":"https://www.wikidata.org/wiki/Q864217","display_name":"Biobank","level":2,"score":0.8719680309295654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504745721817017},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6051023602485657},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5609155893325806},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4794924855232239},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.47429612278938293},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4585355222225189},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.43204864859580994},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41104644536972046},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.24646177887916565},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08579617738723755},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08038723468780518},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07981038093566895},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","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":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018070","descriptor_name":"Biological Specimen Banks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btaa628","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa628","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/19/4951/40418615/btaa628.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:32756942","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32756942","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:scholarsphere.psu.edu:f3d13bab-c12a-44ba-9585-7ec208269007","is_oa":false,"landing_page_url":"https://scholarsphere.psu.edu/resources/f3d13bab-c12a-44ba-9585-7ec208269007","pdf_url":null,"source":{"id":"https://openalex.org/S4306401507","display_name":"ScholarSphere (Penn State Libraries)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I3130638595","host_organization_name":"Pangasinan State University","host_organization_lineage":["https://openalex.org/I3130638595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:europepmc.org:7346724","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8453228","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8453228","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8453228","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/btaa628","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa628","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/19/4951/40418615/btaa628.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":[{"id":"https://metadata.un.org/sdg/9","score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1074740118","display_name":null,"funder_award_id":"R01 GM126479","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G2173156417","display_name":null,"funder_award_id":"R01 HG 008983","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G2500507575","display_name":null,"funder_award_id":"R01GM126479","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G434004855","display_name":null,"funder_award_id":"R56 HG011035","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G8479980234","display_name":null,"funder_award_id":"R01HG008983","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3047494315.pdf","grobid_xml":"https://content.openalex.org/works/W3047494315.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W783262033","https://openalex.org/W2108234281","https://openalex.org/W2124165778","https://openalex.org/W2136939537","https://openalex.org/W2142386149","https://openalex.org/W2280860630","https://openalex.org/W2727352277","https://openalex.org/W2895486342"],"related_works":["https://openalex.org/W3113746618","https://openalex.org/W4226051228","https://openalex.org/W3017691140","https://openalex.org/W2024651825","https://openalex.org/W4384208482","https://openalex.org/W4244742767","https://openalex.org/W2470939431","https://openalex.org/W4226156868","https://openalex.org/W2323349009","https://openalex.org/W4248738672"],"abstract_inverted_index":{"SUMMARY:":[0],"Here,":[1],"we":[2],"present":[3],"a":[4,32],"highly":[5],"efficient":[6],"R-package":[7],"seqminer2":[8,104],"for":[9,36,63,80,113],"querying":[10,37],"and":[11,23,46,65,77,90],"retrieving":[12],"sequence":[13,96],"variants":[14],"from":[15,109],"biobank":[16,94],"scale":[17,95],"datasets":[18,97],"of":[19,21,25,27,44,93],"millions":[20,26],"individuals":[22],"hundreds":[24],"genetic":[28],"variants.":[29],"Seqminer2":[30],"implements":[31],"novel":[33],"variant-based":[34],"index":[35],"VCF/BCF":[38],"files.":[39],"It":[40,59],"improves":[41,69],"the":[42,53,114],"speed":[43,70],"query":[45],"retrieval":[47],"by":[48],"several":[49],"magnitudes":[50],"compared":[51],"to":[52],"state-of-the-art":[54],"tools":[55],"based":[56],"upon":[57],"tabix.":[58],"also":[60],"reimplements":[61],"support":[62,79],"BGEN":[64],"PLINK":[66],"format,":[67],"which":[68],"over":[71],"alternative":[72],"implementations.":[73],"The":[74,103],"improved":[75],"efficiency":[76],"comprehensive":[78],"popular":[81],"file":[82],"formats":[83],"will":[84],"facilitate":[85],"method":[86],"development,":[87],"software":[88],"prototyping":[89],"data":[91,123],"analysis":[92],"in":[98,118],"R.":[99],"AVAILABILITY":[100],"AND":[101],"IMPLEMENTATION:":[102],"R":[105],"package":[106],"is":[107],"available":[108,117,125],"https://github.com/zhanxw/seqminer.":[110],"Scripts":[111],"used":[112],"benchmarks":[115],"are":[116,124],"https://github.com/yang-lina/seqminer/blob/master/seqminer2%20benchmark%20script.txt.":[119],"SUPPLEMENTARY":[120],"INFORMATION:":[121],"Supplementary":[122],"at":[126],"Bioinformatics":[127],"online.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
