{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:49Z","timestamp":1772138089807,"version":"3.50.1"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T00:00:00Z","timestamp":1531958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DBI-1356529"],"award-info":[{"award-number":["DBI-1356529"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF1439057"],"award-info":[{"award-number":["CCF1439057"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-1453527"],"award-info":[{"award-number":["IIS-1453527"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Genotyping a set of variants from a database is an important step for identifying known genetic traits and disease-related variants within an individual. The growing size of variant databases as well as the high depth of sequencing data poses an efficiency challenge. In clinical applications, where time is crucial, alignment-based methods are often not fast enough. To fill the gap, Shajii et al. propose LAVA, an alignment-free genotyping method which is able to more quickly genotype single nucleotide polymorphisms (SNPs); however, there remains large room for improvements in running time and accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present the VarGeno method for SNP genotyping from Illumina whole genome sequencing data. VarGeno builds upon LAVA by improving the speed of k-mer querying as well as the accuracy of the genotyping strategy. We evaluate VarGeno on several read datasets using different genotyping SNP lists. VarGeno performs 7\u201313 times faster than LAVA with similar memory usage, while improving accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>VarGeno is freely available at: https:\/\/github.com\/medvedevgroup\/vargeno.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/bty641","type":"journal-article","created":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T06:12:23Z","timestamp":1531980743000},"page":"415-420","source":"Crossref","is-referenced-by-count":32,"title":["Toward fast and accurate SNP genotyping from whole genome sequencing data for bedside diagnostics"],"prefix":"10.1093","volume":"35","author":[{"given":"Chen","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Pennsylvania State University, USA"}]},{"given":"Paul","family":"Medvedev","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Pennsylvania State University, USA"},{"name":"Department of Biochemistry and Molecular Biology, Pennsylvania State University, USA"},{"name":"Center for Computational Biology and Bioinformatics, Pennsylvania State University, USA"}]}],"member":"286","published-online":{"date-parts":[[2018,7,19]]},"reference":[{"key":"2023013107242155200_bty641-B1","doi-asserted-by":"crossref","first-page":"56.","DOI":"10.1038\/nature11632","article-title":"An integrated map of genetic variation from 1, 092 human genomes","volume":"491","author":"1000 Genomes Project Consortium","year":"2012","journal-title":"Nature"},{"key":"2023013107242155200_bty641-B2","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1145\/362686.362692","article-title":"Space\/time trade-offs in hash coding with allowable errors","volume":"13","author":"Bloom","year":"1970","journal-title":"Commun. ACM"},{"key":"2023013107242155200_bty641-B3","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1038\/nbt.3519","article-title":"Near-optimal probabilistic RNA-seq quantification","volume":"34","author":"Bray","year":"2016","journal-title":"Nat. Biotech"},{"key":"2023013107242155200_bty641-B4","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1080\/15427951.2004.10129096","article-title":"Network applications of Bloom filters: a survey","volume":"1","author":"Broder","year":"2004","journal-title":"Internet Mathematics"},{"key":"2023013107242155200_bty641-B5","doi-asserted-by":"crossref","first-page":"491.","DOI":"10.1038\/ng.806","article-title":"A framework for variation discovery and genotyping using next-generation DNA sequencing data","volume":"43","author":"DePristo","year":"2011","journal-title":"Nat. Genet"},{"key":"2023013107242155200_bty641-B6","first-page":"3907","article-title":"Haplotype-based variant detection from short-read sequencing","volume":"1207","author":"Garrison","year":"2012","journal-title":"arXiv Preprint arXiv"},{"key":"2023013107242155200_bty641-B7","doi-asserted-by":"crossref","first-page":"95.","DOI":"10.1038\/nrg1521","article-title":"Genome-wide association studies for common diseases and complex traits","volume":"6","author":"Hirschhorn","year":"2005","journal-title":"Nat. Rev. Genet"},{"key":"2023013107242155200_bty641-B8","doi-asserted-by":"crossref","first-page":"4181","DOI":"10.1093\/nar\/gkp552","article-title":"Single nucleotide polymorphism arrays: a decade of biological, computational and technological advances","volume":"37","author":"LaFramboise","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2023013107242155200_bty641-B9","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1093\/bioinformatics\/btp698","article-title":"Fast and accurate long-read alignment with Burrows\u2013Wheeler transform","volume":"26","author":"Li","year":"2010","journal-title":"Bioinformatics"},{"key":"2023013107242155200_bty641-B10","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The sequence alignment\/map format and SAMtools","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2023013107242155200_bty641-B11","doi-asserted-by":"crossref","first-page":"981.","DOI":"10.1038\/nrg1226","article-title":"The power and promise of population genomics: from genotyping to genome typing","volume":"4","author":"Luikart","year":"2003","journal-title":"Nat. Rev. Genet"},{"key":"2023013107242155200_bty641-B12","doi-asserted-by":"crossref","first-page":"1166.","DOI":"10.1038\/ng.238","article-title":"Integrated detection and population-genetic analysis of SNPs and copy number variation","volume":"40","author":"McCarroll","year":"2008","journal-title":"Nat. Genet"},{"key":"2023013107242155200_bty641-B13","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1101\/gr.107524.110","article-title":"The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data","volume":"20","author":"McKenna","year":"2010","journal-title":"Genome Res"},{"key":"2023013107242155200_bty641-B14","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1093\/bioinformatics\/btw044","article-title":"BCFtools\/RoH: a hidden Markov model approach for detecting autozygosity from next-generation sequencing data","volume":"32","author":"Narasimhan","year":"2016","journal-title":"Bioinformatics"},{"key":"2023013107242155200_bty641-B15","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1101\/gr.10.7.1031","article-title":"A system for specific, high-throughput genotyping by allele-specific primer extension on microarrays","volume":"10","author":"Pastinen","year":"2000","journal-title":"Genome Res"},{"key":"2023013107242155200_bty641-B16","doi-asserted-by":"crossref","first-page":"417.","DOI":"10.1038\/nmeth.4197","article-title":"Salmon provides fast and bias-aware quantification of transcript expression","volume":"14","author":"Patro","year":"2017","journal-title":"Nat. Methods"},{"key":"2023013107242155200_bty641-B17","doi-asserted-by":"crossref","first-page":"S7.","DOI":"10.1186\/1471-2105-15-S9-S7","article-title":"Fast lossless compression via cascading Bloom filters","volume":"15","author":"Rozov","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2023013107242155200_bty641-B18","doi-asserted-by":"crossref","first-page":"i538","DOI":"10.1093\/bioinformatics\/btw460","article-title":"Fast genotyping of known SNPs through approximate k-mer matching","volume":"32","author":"Shajii","year":"2016","journal-title":"Bioinformatics"},{"key":"2023013107242155200_bty641-B19","doi-asserted-by":"crossref","first-page":"300.","DOI":"10.1038\/nbt.3442","article-title":"Fast search of thousands of short-read sequencing experiments","volume":"34","author":"Solomon","year":"2016","journal-title":"Nat. Biotechnol"},{"key":"2023013107242155200_bty641-B20","first-page":"257","volume-title":"International Conference on Research in Computational Molecular Biology","author":"Solomon","year":"2017"},{"key":"2023013107242155200_bty641-B21","doi-asserted-by":"crossref","first-page":"i192","DOI":"10.1093\/bioinformatics\/btw277","article-title":"Rapmap: a rapid, sensitive and accurate tool for mapping RNA-seq reads to transcriptomes","volume":"32","author":"Srivastava","year":"2016","journal-title":"Bioinformatics"},{"key":"2023013107242155200_bty641-B22","first-page":"272","volume-title":"International Conference on Research in Computational Molecular Biology","author":"Sun","year":"2017"},{"key":"2023013107242155200_bty641-B23","doi-asserted-by":"crossref","first-page":"S5","DOI":"10.1038\/ng1558","article-title":"Toward genome-wide SNP genotyping","volume":"37","author":"Syv\u00e4nen","year":"2005","journal-title":"Nat. Genet"},{"key":"2023013107242155200_bty641-B24","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1093\/bioinformatics\/btg005","article-title":"Alignment-free sequence comparison - a review","volume":"19","author":"Vinga","year":"2003","journal-title":"Bioinformatics"},{"key":"2023013107242155200_bty641-B25","doi-asserted-by":"crossref","first-page":"246.","DOI":"10.1038\/nbt.2835","article-title":"Integrating human sequence data sets provides a resource of benchmark SNP and indel genotype calls","volume":"32","author":"Zook","year":"2014","journal-title":"Nat. Biotechnol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/3\/415\/48964899\/bioinformatics_35_3_415.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/3\/415\/48964899\/bioinformatics_35_3_415.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T05:16:45Z","timestamp":1675142205000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/3\/415\/5056043"}},"subtitle":[],"editor":[{"given":"Bonnie","family":"Berger","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2018,7,19]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,2,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty641","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/239871","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,2,1]]},"published":{"date-parts":[[2018,7,19]]}}}