{"id":"https://openalex.org/W2157905021","doi":"https://doi.org/10.1093/bioinformatics/btu706","title":"Using 2<i>k</i>\u2009+\u20092 bubble searches to find single nucleotide polymorphisms in <i>k</i>-mer graphs","display_name":"Using 2<i>k</i>\u2009+\u20092 bubble searches to find single nucleotide polymorphisms in <i>k</i>-mer graphs","publication_year":2014,"publication_date":"2014-10-24","ids":{"openalex":"https://openalex.org/W2157905021","doi":"https://doi.org/10.1093/bioinformatics/btu706","mag":"2157905021","pmid":"https://pubmed.ncbi.nlm.nih.gov/25344498"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu706","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu706","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/5/642/49011486/bioinformatics_31_5_642.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/31/5/642/49011486/bioinformatics_31_5_642.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009794128","display_name":"Reda Younsi","orcid":"https://orcid.org/0000-0003-1622-6816"},"institutions":[{"id":"https://openalex.org/I2799300731","display_name":"Norwich Research Park","ror":"https://ror.org/0062dz060","country_code":"GB","type":"archive","lineage":["https://openalex.org/I2799300731"]},{"id":"https://openalex.org/I2800011936","display_name":"Sainsbury Laboratory","ror":"https://ror.org/02tdtzx53","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2800011936"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Reda Younsi","raw_affiliation_strings":["1The Sainsbury Laboratory, Norwich Research Park, Norwich NR4 7UH, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1The Sainsbury Laboratory, Norwich Research Park, Norwich NR4 7UH, UK","institution_ids":["https://openalex.org/I2800011936","https://openalex.org/I2799300731"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044324735","display_name":"Dan MacLean","orcid":"https://orcid.org/0000-0003-1032-0887"},"institutions":[{"id":"https://openalex.org/I2799300731","display_name":"Norwich Research Park","ror":"https://ror.org/0062dz060","country_code":"GB","type":"archive","lineage":["https://openalex.org/I2799300731"]},{"id":"https://openalex.org/I2800011936","display_name":"Sainsbury Laboratory","ror":"https://ror.org/02tdtzx53","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2800011936"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dan MacLean","raw_affiliation_strings":["1The Sainsbury Laboratory, Norwich Research Park, Norwich NR4 7UH, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1The Sainsbury Laboratory, Norwich Research Park, Norwich NR4 7UH, UK","institution_ids":["https://openalex.org/I2800011936","https://openalex.org/I2799300731"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009794128"],"corresponding_institution_ids":["https://openalex.org/I2799300731","https://openalex.org/I2800011936"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.6978,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76348489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"31","issue":"5","first_page":"642","last_page":"646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.4659999907016754,"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":0.4659999907016754,"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":0.17640000581741333,"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/T10012","display_name":"Genetic diversity and population structure","score":0.16529999673366547,"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/de-bruijn-graph","display_name":"De Bruijn graph","score":0.7966032028198242},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.7484212517738342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5349339842796326},{"id":"https://openalex.org/keywords/snp","display_name":"SNP","score":0.5331135988235474},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphism","display_name":"Single-nucleotide polymorphism","score":0.5218688249588013},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4324786067008972},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.41299015283584595},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.35349029302597046},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3439640402793884},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3277796506881714},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3223445415496826},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.21841028332710266},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19357535243034363},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.16730821132659912},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.1128419041633606}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.7966032028198242},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.7484212517738342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5349339842796326},{"id":"https://openalex.org/C139275648","wikidata":"https://www.wikidata.org/wiki/Q17134011","display_name":"SNP","level":5,"score":0.5331135988235474},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.5218688249588013},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4324786067008972},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41299015283584595},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.35349029302597046},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3439640402793884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3277796506881714},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3223445415496826},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.21841028332710266},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19357535243034363},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.16730821132659912},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.1128419041633606}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":"Q000235","qualifier_name":"genetics","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":4,"locations":[{"id":"doi:10.1093/bioinformatics/btu706","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu706","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/5/642/49011486/bioinformatics_31_5_642.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:25344498","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25344498","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:ueaeprints.uea.ac.uk:77609","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:europepmc.org:3319910","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4341063","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btu706","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu706","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/5/642/49011486/bioinformatics_31_5_642.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G1449695204","display_name":null,"funder_award_id":"BB/I023798/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"},{"id":"https://openalex.org/G4359341121","display_name":"Tool for finding linked genetic polymorphisms in reference-less complex plant genomes from unassembled next-generation reads.","funder_award_id":"BB/I023798/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320033","display_name":"Gatsby Charitable Foundation","ror":"https://ror.org/0290hax27"},{"id":"https://openalex.org/F4320332167","display_name":"Directorate for Biological Sciences","ror":"https://ror.org/001xhss06"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2157905021.pdf","grobid_xml":"https://content.openalex.org/works/W2157905021.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1494075612","https://openalex.org/W1532744586","https://openalex.org/W1966822396","https://openalex.org/W2010361633","https://openalex.org/W2043621752","https://openalex.org/W2055043387","https://openalex.org/W2079507916","https://openalex.org/W2096981901","https://openalex.org/W2103441770","https://openalex.org/W2108234281","https://openalex.org/W2133990480","https://openalex.org/W2136651963","https://openalex.org/W2149706766","https://openalex.org/W2160969485","https://openalex.org/W2166469005","https://openalex.org/W2292996153","https://openalex.org/W4236137412"],"related_works":["https://openalex.org/W2562683361","https://openalex.org/W3087469195","https://openalex.org/W3125399386","https://openalex.org/W2354744388","https://openalex.org/W2949121831","https://openalex.org/W3215786367","https://openalex.org/W2756186577","https://openalex.org/W2735897904","https://openalex.org/W1908987670","https://openalex.org/W2025111520"],"abstract_inverted_index":{"MOTIVATION:":[0],"Single":[1],"nucleotide":[2],"polymorphism":[3],"(SNP)":[4],"discovery":[5],"is":[6,217,246],"an":[7,76,123],"important":[8],"preliminary":[9],"for":[10,239],"understanding":[11],"genetic":[12,73],"variation.":[13],"With":[14],"current":[15],"sequencing":[16],"methods,":[17],"we":[18],"can":[19,42],"sample":[20],"genomes":[21],"comprehensively.":[22],"SNPs":[23,127,145,221],"are":[24,37,96,262],"found":[25,171,177],"by":[26,133,146],"aligning":[27],"sequence":[28,162],"reads":[29],"against":[30],"longer":[31],"assembled":[32],"references.":[33],"De":[34,130],"Bruijn":[35,131],"graphs":[36,62,132],"efficient":[38],"data":[39,49,163],"structures":[40],"that":[41,57,125,172,178,214],"deal":[43],"with":[44,148],"the":[45,58,68,88,111,141,158,184,194,249,265],"vast":[46],"amount":[47],"of":[48,60,72,87,110,116,143,157,167,193,206,219,243],"from":[50,151,164,229],"modern":[51],"technologies.":[52],"Recent":[53],"work":[54],"has":[55],"shown":[56],"topology":[59],"these":[61,211],"captures":[63],"enough":[64],"information":[65],"to":[66,78,90,196,203],"allow":[67],"detection":[69],"and":[70,170,186,226],"characterization":[71],"variants,":[74],"offering":[75],"alternative":[77],"alignment-based":[79,152],"methods.":[80,153],"Such":[81],"methods":[82,95],"rely":[83],"on":[84],"depth-first":[85],"walks":[86],"graph":[89,112,195],"identify":[91],"closing":[92],"bifurcations.":[93],"These":[94],"conservative":[97],"or":[98,113],"generate":[99],"many":[100],"false-positive":[101],"results,":[102],"particularly":[103],"when":[104],"traversing":[105],"highly":[106],"inter-connected":[107],"(complex)":[108],"regions":[109,115],"in":[114,128,223,259],"very":[117],"high":[118],"coverage.":[119],"RESULTS:":[120],"We":[121,139,154,176],"devised":[122],"algorithm":[124,216,245],"calls":[126,208],"converted":[129],"enumerating":[134],"2k":[135],"+":[136],"2":[137],"cycles.":[138],"evaluated":[140],"accuracy":[142,156,173,205],"predicted":[144],"comparison":[147],"SNP":[149,159,179,207],"lists":[150],"tested":[155],"calling":[160,180],"using":[161],"16":[165],"ecotypes":[166],"Arabidopsis":[168],"thaliana":[169],"was":[174,181],"high.":[175],"even":[182],"across":[183],"genome":[185,231],"genomic":[187],"feature":[188],"types.":[189],"Using":[190],"sequence-based":[191],"attributes":[192],"train":[197],"a":[198,240],"decision":[199],"tree":[200],"allowed":[201],"us":[202],"increase":[204],"further.":[209],"Together":[210],"results":[212],"indicate":[213],"our":[215,244],"capable":[218],"finding":[220],"accurately":[222],"complex":[224],"sub-graphs":[225],"potentially":[227],"comprehensively":[228],"whole":[230],"graphs.":[232],"AVAILABILITY":[233],"AND":[234],"IMPLEMENTATION:":[235],"The":[236,256],"source":[237],"code":[238],"C++":[241],"implementation":[242],"available":[247,263],"under":[248],"GNU":[250],"Public":[251],"Licence":[252],"v3":[253],"at:":[254],"https://github.com/danmaclean/2kplus2.":[255],"datasets":[257],"used":[258],"this":[260],"study":[261],"at":[264],"European":[266],"Nucleotide":[267],"Archive,":[268],"reference":[269],"ERP00565,":[270],"http://www.ebi.ac.uk/ena/data/view/ERP000565.":[271]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}
