{"id":"https://openalex.org/W2980477453","doi":"https://doi.org/10.1093/bioinformatics/btz782","title":"An improved encoding of genetic variation in a Burrows\u2013Wheeler transform","display_name":"An improved encoding of genetic variation in a Burrows\u2013Wheeler transform","publication_year":2019,"publication_date":"2019-10-11","ids":{"openalex":"https://openalex.org/W2980477453","doi":"https://doi.org/10.1093/bioinformatics/btz782","mag":"2980477453","pmid":"https://pubmed.ncbi.nlm.nih.gov/31613311"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz782","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz782","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/5/1413/32793867/btz782.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/36/5/1413/32793867/btz782.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088688063","display_name":"Thomas B\u00fcchler","orcid":"https://orcid.org/0000-0002-9273-5439"},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas B\u00fcchler","raw_affiliation_strings":["Institute of Theoretical Computer Science, Ulm University , Ulm 89069, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Theoretical Computer Science, Ulm University , Ulm 89069, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090763399","display_name":"Enno Ohlebusch","orcid":"https://orcid.org/0009-0008-3937-3652"},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Enno Ohlebusch","raw_affiliation_strings":["Institute of Theoretical Computer Science, Ulm University , Ulm 89069, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Theoretical Computer Science, Ulm University , Ulm 89069, Germany","institution_ids":["https://openalex.org/I196349391"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5090763399"],"corresponding_institution_ids":["https://openalex.org/I196349391"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.2282,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.52068107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"36","issue":"5","first_page":"1413","last_page":"1419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.49230000376701355,"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":"Genomics and Phylogenetic Studies","score":0.49230000376701355,"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/T11269","display_name":"Algorithms and Data Compression","score":0.30399999022483826,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13664","display_name":"Genome Rearrangement Algorithms","score":0.05209999904036522,"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/encode","display_name":"ENCODE","score":0.6244742274284363},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.6041492223739624},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5838721990585327},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphism","display_name":"Single-nucleotide polymorphism","score":0.5406363606452942},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4959295690059662},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4908655285835266},{"id":"https://openalex.org/keywords/structural-variation","display_name":"Structural variation","score":0.45890161395072937},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.45489755272865295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44131559133529663},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4365043044090271},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.4305906295776367},{"id":"https://openalex.org/keywords/dbsnp","display_name":"dbSNP","score":0.42040833830833435},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.37512218952178955},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.25221118330955505},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.14517274498939514},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.11703625321388245},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10552889108657837}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6244742274284363},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.6041492223739624},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5838721990585327},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.5406363606452942},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4959295690059662},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4908655285835266},{"id":"https://openalex.org/C151020129","wikidata":"https://www.wikidata.org/wiki/Q7625067","display_name":"Structural variation","level":4,"score":0.45890161395072937},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.45489755272865295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44131559133529663},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4365043044090271},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.4305906295776367},{"id":"https://openalex.org/C35794970","wikidata":"https://www.wikidata.org/wiki/Q5243761","display_name":"dbSNP","level":5,"score":0.42040833830833435},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.37512218952178955},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.25221118330955505},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.14517274498939514},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.11703625321388245},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10552889108657837},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":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":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btz782","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz782","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/5/1413/32793867/btz782.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:31613311","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31613311","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/btz782","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz782","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/5/1413/32793867/btz782.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/G6215124692","display_name":null,"funder_award_id":"OH 53/7-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8317225305","display_name":null,"funder_award_id":"OH 53/7-1","funder_id":"https://openalex.org/F4320308022","funder_display_name":"California Department of Fish and Game"}],"funders":[{"id":"https://openalex.org/F4320308022","display_name":"California Department of Fish and Game","ror":"https://ror.org/02v6w2r95"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1976682045","https://openalex.org/W1978173716","https://openalex.org/W2099642610","https://openalex.org/W2103441770","https://openalex.org/W2104549677","https://openalex.org/W2137351413","https://openalex.org/W2161488606","https://openalex.org/W2168909179","https://openalex.org/W2170551349","https://openalex.org/W2407929722"],"related_works":["https://openalex.org/W2150917858","https://openalex.org/W204227468","https://openalex.org/W2962729514","https://openalex.org/W2949103014","https://openalex.org/W2088306096","https://openalex.org/W2155537421","https://openalex.org/W4387216472","https://openalex.org/W3005884313","https://openalex.org/W1973260443","https://openalex.org/W2531667759"],"abstract_inverted_index":{"MOTIVATION:":[0],"In":[1,112,171,292],"resequencing":[2],"experiments,":[3],"a":[4,21,52,98,113,120,130,137,154,176,201,261,311,346],"high-throughput":[5],"sequencer":[6],"produces":[7],"DNA-fragments":[8],"(called":[9],"reads)":[10],"and":[11,78,106,125,197,234,267,313,364,369],"each":[12],"read":[13,31,41,69,225,339],"is":[14,48,179,335],"then":[15],"mapped":[16,44],"to":[17,51,72,181,264,294],"the":[18,36,55,60,76,101,159,205,214,235,238,246,273,321,324,330,353,358],"locus":[19],"in":[20,97,129,136,200,219,249,260,279,286,310,337,344,357],"reference":[22,56,61,77],"genome":[23,62,268],"at":[24,320],"which":[25,151,317,334],"it":[26,47,349,366],"fits":[27],"best.":[28],"Currently":[29],"dominant":[30],"mappers":[32],"are":[33,211,318],"based":[34],"on":[35,245,277],"Burrows-Wheeler":[37,262],"transform":[38,263],"(BWT).":[39],"A":[40,254],"can":[42,145,341,350],"be":[43,73,342],"correctly":[45],"if":[46],"similar":[49],"enough":[50],"substring":[53],"of":[54,104,123,148,156,168,185,207,229,237,241,257,272,283,323],"genome.":[57],"However,":[58,132],"since":[59],"does":[63],"not":[64,163],"represent":[65],"all":[66,165],"known":[67,166],"variations,":[68],"mapping":[70,79,266],"tends":[71],"biased":[74],"towards":[75],"errors":[80],"may":[81],"thus":[82],"occur.":[83],"To":[84],"cope":[85,351],"with":[86,227,352,367],"this":[87,172],"problem,":[88],"Huang":[89,220],"et":[90,117,221,251,296],"al.":[91,118,222,252],"encoded":[92,212,356],"single":[93],"nucleotide":[94,110,216],"polymorphisms":[95],"(SNPs)":[96],"BWT":[99],"by":[100,213],"International":[102,275],"Union":[103],"Pure":[105],"Applied":[107],"Chemistry":[108],"(IUPAC)":[109],"code.":[111],"different":[114],"approach,":[115],"Maciuca":[116,250,295],"provided":[119],"'natural":[121],"encoding'":[122],"SNPs":[124,210],"other":[126,239],"genetic":[127,186,242,258,354],"variations":[128],"BWT.":[131,202,359],"their":[133],"encoding":[134,236,256],"resulted":[135],"significantly":[138],"increased":[139],"alphabet":[140,144],"size":[141],"(the":[142],"modified":[143,343],"have":[146],"millions":[147],"new":[149],"symbols,":[150],"usually":[152],"implies":[153],"loss":[155],"efficiency).":[157],"Moreover,":[158],"two":[160],"approaches":[161],"do":[162],"handle":[164],"kinds":[167,184,240],"variation.":[169],"RESULTS:":[170],"article,":[173],"we":[174,299],"propose":[175],"method":[177,363],"that":[178,348],"able":[180],"encode":[182],"many":[183],"variation":[187,243,259,355],"(SNPs,":[188],"multi-nucleotide":[189],"polymorphisms,":[190],"insertions":[191],"or":[192],"deletions,":[193],"duplications,":[194],"transpositions,":[195],"inversions":[196],"copy-number":[198],"variation)":[199],"It":[203],"takes":[204],"best":[206],"both":[208],"worlds:":[209],"IUPAC":[215],"code":[217],"as":[218],"(2013,":[223],"Short":[224],"alignment":[226],"populations":[228],"genomes.":[230],"Bioinformatics,":[231,280],"29,":[232],"i361-i370)":[233],"relies":[244],"idea":[247],"introduced":[248],"(2016,":[253],"natural":[255],"enable":[265],"inference.":[269],"In:":[270],"Proceedings":[271],"16th":[274],"Workshop":[276],"Algorithms":[278],"Volume":[281],"9838":[282],"Lecture":[284],"Notes":[285],"Computer":[287],"Science,":[288],"pp.":[289],"222-233.":[290],"Springer).":[291],"contrast":[293],"al.,":[297],"however,":[298],"use":[300],"only":[301],"one":[302],"additional":[303],"symbol.":[304],"This":[305],"symbol":[306],"marks":[307],"variant":[308],"sites":[309],"chromosome":[312],"delimits":[314],"multiple":[315],"variants,":[316],"added":[319],"end":[322],"'marked":[325],"chromosome'.":[326],"We":[327,360],"show":[328],"how":[329],"backward":[331],"search":[332],"algorithm,":[333],"used":[336],"BWT-based":[338],"mappers,":[340],"such":[345],"way":[347],"implemented":[361],"our":[362],"compared":[365],"BWBBLE":[368],"gramtools.":[370],"AVAILABILITY":[371],"AND":[372],"IMPLEMENTATION:":[373],"https://www.uni-ulm.de/in/theo/research/seqana/.":[374]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}
