{"id":"https://openalex.org/W2515342656","doi":"https://doi.org/10.1093/bioinformatics/btw460","title":"Fast genotyping of known SNPs through approximate k-mer matching","display_name":"Fast genotyping of known SNPs through approximate k-mer matching","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2515342656","doi":"https://doi.org/10.1093/bioinformatics/btw460","mag":"2515342656","pmid":"https://pubmed.ncbi.nlm.nih.gov/27587672","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/5013917"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw460","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/17/i538/24151373/btw460.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4811","1367-4803"],"is_oa":true,"is_in_doaj":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":"cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/32/17/i538/24151373/btw460.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061029430","display_name":"Ariya Shajii","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariya Shajii","raw_affiliation_string":"Department of Electrical & Computer Engineering, Boston University, Boston, MA 02215, USA,","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Boston University, Boston, MA 02215, USA,"]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084788599","display_name":"Deniz Y\u00f6r\u00fcko\u011flu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deniz Yorukoglu","raw_affiliation_string":"Computer Science and AI Lab","raw_affiliation_strings":["Computer Science and AI Lab"]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015501574","display_name":"Yun William Yu","orcid":"https://orcid.org/0000-0002-8275-9576"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun William Yu","raw_affiliation_string":"Computer Science and AI Lab; Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","raw_affiliation_strings":["Computer Science and AI Lab","Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"]},{"author_position":"last","author":{"id":"https://openalex.org/A5044078921","display_name":"Bonnie Berger","orcid":"https://orcid.org/0000-0002-2724-7228"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bonnie Berger","raw_affiliation_string":"Computer Science and AI Lab; Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","raw_affiliation_strings":["Computer Science and AI Lab","Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA"]}],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044078921"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618,"provenance":"doaj"},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618,"provenance":"doaj"},"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":51,"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"32","issue":"17","first_page":"i538","last_page":"i544"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"RNA Sequencing Data Analysis","score":0.9988,"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":"RNA Sequencing Data Analysis","score":0.9988,"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/T12254","display_name":"Prediction of Protein Subcellular Localization","score":0.9975,"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/T11213","display_name":"Genomic Rearrangements and Copy Number Variations","score":0.9961,"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":[{"keyword":"fast genotyping","score":0.5737},{"keyword":"snps","score":0.5428},{"keyword":"matching","score":0.4257}],"concepts":[{"id":"https://openalex.org/C35794970","wikidata":"https://www.wikidata.org/wiki/Q5243761","display_name":"dbSNP","level":5,"score":0.84442604},{"id":"https://openalex.org/C31467283","wikidata":"https://www.wikidata.org/wiki/Q912147","display_name":"Genotyping","level":4,"score":0.7315709},{"id":"https://openalex.org/C59701697","wikidata":"https://www.wikidata.org/wiki/Q6895959","display_name":"Molecular Inversion Probe","level":5,"score":0.5799548},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.5484411},{"id":"https://openalex.org/C163691529","wikidata":"https://www.wikidata.org/wiki/Q7391886","display_name":"SNP genotyping","level":5,"score":0.52819645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4788137},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4761912},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.46074665},{"id":"https://openalex.org/C55060382","wikidata":"https://www.wikidata.org/wiki/Q7675093","display_name":"Tag SNP","level":5,"score":0.4569694},{"id":"https://openalex.org/C139275648","wikidata":"https://www.wikidata.org/wiki/Q17134011","display_name":"SNP","level":5,"score":0.45218226},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.42884228},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.38979852},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.1891168},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.124801576},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000483","descriptor_name":"Alleles","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw460","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/17/i538/24151373/btw460.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4811","1367-4803"],"is_oa":true,"is_in_doaj":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":"cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/115481","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/115481/1/btw460.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":["Massachusetts Institute of Technology"],"type":"repository"},"license":"cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://europepmc.org/articles/pmc5013917","pdf_url":"https://europepmc.org/articles/pmc5013917?pdf=render","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":["European Bioinformatics Institute"],"type":"repository"},"license":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5013917","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,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://doi.org/10.1101/063446","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2016/07/12/063446.full.pdf","source":null,"license":"cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27587672","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":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":["National Institutes of Health"],"type":"repository"},"license":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw460","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/17/i538/24151373/btw460.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4811","1367-4803"],"is_oa":true,"is_in_doaj":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311647","https://openalex.org/P4310311648"],"host_organization_lineage_names":["University of Oxford","Oxford University Press"],"type":"journal"},"license":"cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320306082","funder_display_name":"Howard Hughes Medical Institute","award_id":null},{"funder":"https://openalex.org/F4320307762","funder_display_name":"International Business Machines Corporation","award_id":null},{"funder":"https://openalex.org/F4320308782","funder_display_name":"Hertz Foundation","award_id":null},{"funder":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health","award_id":null}],"referenced_works_count":32,"referenced_works":["https://openalex.org/W1532744586","https://openalex.org/W1866835760","https://openalex.org/W1976369775","https://openalex.org/W1997455636","https://openalex.org/W2003347102","https://openalex.org/W2021003438","https://openalex.org/W2025648894","https://openalex.org/W2044805330","https://openalex.org/W2057791956","https://openalex.org/W2062772087","https://openalex.org/W2069066547","https://openalex.org/W2074490119","https://openalex.org/W2096791516","https://openalex.org/W2103441770","https://openalex.org/W2107903949","https://openalex.org/W2108234281","https://openalex.org/W2119180969","https://openalex.org/W2119279196","https://openalex.org/W2122732537","https://openalex.org/W2128162768","https://openalex.org/W2129103781","https://openalex.org/W2129714591","https://openalex.org/W2141831115","https://openalex.org/W2159954944","https://openalex.org/W2167669612","https://openalex.org/W2168133698","https://openalex.org/W2170551349","https://openalex.org/W2171963266","https://openalex.org/W2320964193","https://openalex.org/W2323326409","https://openalex.org/W2488449982","https://openalex.org/W4233928114"],"related_works":["https://openalex.org/W1504890006","https://openalex.org/W2019337456","https://openalex.org/W2061407956","https://openalex.org/W45489710","https://openalex.org/W2145418365","https://openalex.org/W2954446872","https://openalex.org/W2377243617","https://openalex.org/W2149788957","https://openalex.org/W2168919926","https://openalex.org/W3139651602"],"ngrams_url":"https://api.openalex.org/works/W2515342656/ngrams","abstract_inverted_index":{"As":[0,192],"the":[1,28,41,81,115,133,143],"volume":[2],"of":[3,18,31,40,43,49,56,67,84,96,108,114,120,146,162,190],"next-generation":[4],"sequencing":[5],"(NGS)":[6],"data":[7,219],"increases,":[8],"faster":[9,164],"algorithms":[10],"become":[11],"necessary.":[12],"Although":[13],"speeding":[14],"up":[15,157],"individual":[16],"components":[17],"a":[19,44,53,105,196,207],"sequence":[20],"analysis":[21],"pipeline":[22],"(e.g.":[23,58,91],"read":[24,138],"mapping)":[25],"can":[26,127],"reduce":[27],"computational":[29,198],"cost":[30],"analysis,":[32],"such":[33],"approaches":[34],"do":[35],"not":[36],"take":[37],"full":[38,137],"advantage":[39,113],"particulars":[42],"given":[45,106],"problem.":[46],"One":[47],"problem":[48],"great":[50],"interest,":[51],"genotyping":[52,102,168,202],"known":[54,68],"set":[55,107],"variants":[57,74],"dbSNP":[59,149],"or":[60],"Affymetrix":[61,171],"SNPs),":[62],"is":[63,215],"important":[64],"for":[65,104,200,211],"characterization":[66],"genetic":[69],"traits":[70],"and":[71,87,150],"causative":[72],"disease":[73],"within":[75],"an":[76,100,160],"individual,":[77],"as":[78,80,185,187,204,206],"well":[79,205],"initial":[82],"stage":[83],"many":[85],"ancestral":[86],"population":[88],"genomic":[89],"pipelines":[90,182],"GWAS).We":[92],"introduce":[93],"lightweight":[94],"assignment":[95],"variant":[97],"alleles":[98],"(LAVA),":[99],"NGS-based":[101,209],"algorithm":[103],"SNP":[109,154,177,212],"loci,":[110],"which":[111],"takes":[112],"fact":[116],"that":[117],"approximate":[118],"matching":[119],"mid-size":[121],"k-mers":[122],"(with":[123],"k":[124],"=":[125],"32)":[126],"typically":[128],"uniquely":[129],"identify":[130],"loci":[131],"in":[132,148],"human":[134],"genome":[135],"without":[136],"alignment.":[139],"LAVA":[140,173,194],"accurately":[141],"calls":[142],"vast":[144],"majority":[145],"SNPs":[147],"Affymetrix's":[151],"Genome-Wide":[152],"Human":[153],"Array":[155],"6.0":[156],"to":[158],"about":[159],"order":[161],"magnitude":[163],"than":[165,180],"standard":[166],"NGS":[167],"pipelines.":[169],"For":[170],"SNPs,":[172],"has":[174],"significantly":[175],"higher":[176],"calling":[178],"accuracy":[179],"existing":[181],"while":[183],"using":[184],"low":[186],"\u223c5":[188],"GB":[189],"RAM.":[191],"such,":[193],"represents":[195],"scalable":[197],"method":[199],"population-level":[201],"studies":[203],"flexible":[208],"replacement":[210],"arrays.LAVA":[213],"software":[214],"available":[216,221],"at":[217,222],"http://lava.csail.mit.edubab@mit.eduSupplementary":[218],"are":[220],"Bioinformatics":[223],"online.":[224]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2515342656","counts_by_year":[{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2024-03-04T12:04:21.427116","created_date":"2016-09-16"}