{"id":"https://openalex.org/W2883729812","doi":"https://doi.org/10.1093/bioinformatics/bty641","title":"Toward fast and accurate SNP genotyping from whole genome sequencing data for bedside diagnostics","display_name":"Toward fast and accurate SNP genotyping from whole genome sequencing data for bedside diagnostics","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2883729812","doi":"https://doi.org/10.1093/bioinformatics/bty641","mag":"2883729812","pmid":"https://pubmed.ncbi.nlm.nih.gov/30032192"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bty641","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty641","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/3/415/27699871/bty641.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/35/3/415/27699871/bty641.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":true,"raw_author_name":"Chen Sun","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, 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":false,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Center for Computational Biology and Bioinformatics, Pennsylvania State University, USA","Department of Biochemistry and Molecular Biology, Pennsylvania State University, USA","Department of Computer Science and Engineering, Pennsylvania State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology and Bioinformatics, Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100722234"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.5303,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.9325355,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"35","issue":"3","first_page":"415","last_page":"420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.7498000264167786,"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":0.7498000264167786,"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":0.18770000338554382,"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":0.02199999988079071,"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/genotyping","display_name":"Genotyping","score":0.874065637588501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6207051277160645},{"id":"https://openalex.org/keywords/snp","display_name":"SNP","score":0.5931766629219055},{"id":"https://openalex.org/keywords/snp-genotyping","display_name":"SNP genotyping","score":0.5694437623023987},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphism","display_name":"Single-nucleotide polymorphism","score":0.544335663318634},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5142640471458435},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4516467750072479},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37330180406570435},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.32830166816711426},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30184274911880493},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.29193249344825745},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08546847105026245}],"concepts":[{"id":"https://openalex.org/C31467283","wikidata":"https://www.wikidata.org/wiki/Q912147","display_name":"Genotyping","level":4,"score":0.874065637588501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6207051277160645},{"id":"https://openalex.org/C139275648","wikidata":"https://www.wikidata.org/wiki/Q17134011","display_name":"SNP","level":5,"score":0.5931766629219055},{"id":"https://openalex.org/C163691529","wikidata":"https://www.wikidata.org/wiki/Q7391886","display_name":"SNP genotyping","level":5,"score":0.5694437623023987},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.544335663318634},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5142640471458435},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4516467750072479},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37330180406570435},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.32830166816711426},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30184274911880493},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.29193249344825745},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08546847105026245}],"mesh":[{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060005","descriptor_name":"Genotyping Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060005","descriptor_name":"Genotyping Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060005","descriptor_name":"Genotyping Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bty641","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty641","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/3/415/27699871/bty641.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:30032192","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30032192","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/bty641","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty641","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/3/415/27699871/bty641.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/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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1596062789","https://openalex.org/W1982335109","https://openalex.org/W1993284846","https://openalex.org/W2021003438","https://openalex.org/W2047361940","https://openalex.org/W2062772087","https://openalex.org/W2066669827","https://openalex.org/W2096791516","https://openalex.org/W2100076391","https://openalex.org/W2103441770","https://openalex.org/W2108234281","https://openalex.org/W2119180969","https://openalex.org/W2123845384","https://openalex.org/W2129359631","https://openalex.org/W2147733682","https://openalex.org/W2168133698","https://openalex.org/W2171963266","https://openalex.org/W2263875137","https://openalex.org/W2266239166","https://openalex.org/W2323326409","https://openalex.org/W2515342656","https://openalex.org/W2560209686","https://openalex.org/W2592811885","https://openalex.org/W2951230321","https://openalex.org/W2952944477","https://openalex.org/W3098304617","https://openalex.org/W4247053599","https://openalex.org/W6635813232"],"related_works":["https://openalex.org/W2377518790","https://openalex.org/W2394359576","https://openalex.org/W2463477745","https://openalex.org/W2349105149","https://openalex.org/W2329658823","https://openalex.org/W1508523048","https://openalex.org/W2070581548","https://openalex.org/W2104756498","https://openalex.org/W2936024166","https://openalex.org/W2970780691"],"abstract_inverted_index":{"Motivation:":[0],"Genotyping":[1],"a":[2,7],"set":[3],"of":[4,27,36,116,124],"variants":[5,20],"from":[6,102],"database":[8],"is":[9,48,71,158],"an":[10,22,40,66],"important":[11],"step":[12],"for":[13,86,99],"identifying":[14],"known":[15],"genetic":[16],"traits":[17],"and":[18,91,155],"disease-related":[19],"within":[21],"individual.":[23],"The":[24],"growing":[25],"size":[26],"variant":[28],"databases":[29],"as":[30,32,119,121],"well":[31,120],"the":[33,59,96,114,122,125],"high":[34],"depth":[35],"sequencing":[37,106],"data":[38,166],"poses":[39],"efficiency":[41],"challenge.":[42],"In":[43],"clinical":[44],"applications,":[45],"where":[46],"time":[47,90],"crucial,":[49],"alignment-based":[50],"methods":[51],"are":[52,167],"often":[53],"not":[54],"fast":[55],"enough.":[56],"To":[57],"fill":[58],"gap,":[60],"Shajii":[61],"et":[62],"al.":[63],"propose":[64],"LAVA,":[65],"alignment-free":[67],"genotyping":[68,101,126,137],"method":[69,98],"which":[70],"able":[72],"to":[73],"more":[74],"quickly":[75],"genotype":[76],"single":[77],"nucleotide":[78],"polymorphisms":[79],"(SNPs);":[80],"however,":[81],"there":[82],"remains":[83],"large":[84],"room":[85],"improvements":[87],"in":[88],"running":[89],"accuracy.":[92,153],"Results:":[93],"We":[94,128],"present":[95],"VarGeno":[97,108,130,140,157],"SNP":[100,138],"Illumina":[103],"whole":[104],"genome":[105],"data.":[107],"builds":[109],"upon":[110],"LAVA":[111,146],"by":[112],"improving":[113,152],"speed":[115],"k-mer":[117],"querying":[118],"accuracy":[123],"strategy.":[127],"evaluate":[129],"on":[131],"several":[132],"read":[133],"datasets":[134],"using":[135],"different":[136],"lists.":[139],"performs":[141],"7-13":[142],"times":[143],"faster":[144],"than":[145],"with":[147],"similar":[148],"memory":[149],"usage,":[150],"while":[151],"Availability":[154],"implementation:":[156],"freely":[159],"available":[160,168],"at:":[161],"https://github.com/medvedevgroup/vargeno.":[162],"Supplementary":[163,165],"information:":[164],"at":[169],"Bioinformatics":[170],"online.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
