{"id":"https://openalex.org/W4288421619","doi":"https://doi.org/10.1145/3535508.3545556","title":"Haplotype-aware variant selection for genome graphs","display_name":"Haplotype-aware variant selection for genome graphs","publication_year":2022,"publication_date":"2022-07-28","ids":{"openalex":"https://openalex.org/W4288421619","doi":"https://doi.org/10.1145/3535508.3545556"},"language":"en","primary_location":{"id":"doi:10.1145/3535508.3545556","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3535508.3545556","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3535508.3545556","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3535508.3545556","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046014937","display_name":"Neda Tavakoli","orcid":"https://orcid.org/0000-0002-1541-5917"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neda Tavakoli","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026282036","display_name":"Daniel Gibney","orcid":"https://orcid.org/0000-0003-1493-5432"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Gibney","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074347913","display_name":"Srinivas Aluru","orcid":"https://orcid.org/0000-0003-4279-469X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Aluru","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046014937"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.5638,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71833993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9972000122070312,"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":0.9972000122070312,"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/T11213","display_name":"Genomic variations and chromosomal abnormalities","score":0.9884999990463257,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.9876000285148621,"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/haplotype","display_name":"Haplotype","score":0.6571899652481079},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.5760760307312012},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.501248836517334},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.4997537136077881},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.495837539434433},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.49039602279663086},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4825541377067566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46207287907600403},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3805401921272278},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3770016133785248},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3591872453689575},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2978631258010864},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2812037467956543},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.17571595311164856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14504238963127136},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1430465281009674},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.11315897107124329}],"concepts":[{"id":"https://openalex.org/C197754878","wikidata":"https://www.wikidata.org/wiki/Q80711","display_name":"Haplotype","level":4,"score":0.6571899652481079},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.5760760307312012},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.501248836517334},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.4997537136077881},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.495837539434433},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.49039602279663086},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4825541377067566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46207287907600403},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3805401921272278},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3770016133785248},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3591872453689575},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2978631258010864},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2812037467956543},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.17571595311164856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14504238963127136},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1430465281009674},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.11315897107124329},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3535508.3545556","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3535508.3545556","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3535508.3545556","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3535508.3545556","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3535508.3545556","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3535508.3545556","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2937413933","display_name":null,"funder_award_id":"CCF-1816027","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3512808941","display_name":"AF: Small: Algorithmic Techniques for High-throughput Analysis of Long Reads","funder_award_id":"1816027","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4288421619.pdf","grobid_xml":"https://content.openalex.org/works/W4288421619.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1621435553","https://openalex.org/W2011210839","https://openalex.org/W2029828838","https://openalex.org/W2115404728","https://openalex.org/W2127901812","https://openalex.org/W2142113273","https://openalex.org/W2143996311","https://openalex.org/W2149992227","https://openalex.org/W2150131459","https://openalex.org/W2278452282","https://openalex.org/W2344013120","https://openalex.org/W2610183793","https://openalex.org/W2759456806","https://openalex.org/W2787131599","https://openalex.org/W2888300707","https://openalex.org/W2955962962","https://openalex.org/W2966459122","https://openalex.org/W3005228641","https://openalex.org/W3012034924","https://openalex.org/W3017152484","https://openalex.org/W3035986830","https://openalex.org/W3043149968","https://openalex.org/W3088400220","https://openalex.org/W3092652421","https://openalex.org/W3100935868","https://openalex.org/W3179119489","https://openalex.org/W4206067192","https://openalex.org/W4248432589","https://openalex.org/W4255836900"],"related_works":["https://openalex.org/W1978042415","https://openalex.org/W1971356995","https://openalex.org/W2088298145","https://openalex.org/W2042848169","https://openalex.org/W2066137273","https://openalex.org/W1202469404","https://openalex.org/W2067577249","https://openalex.org/W2030640333","https://openalex.org/W1990204168","https://openalex.org/W2389073067"],"abstract_inverted_index":{"Graph-based":[0],"genome":[1,84],"representations":[2],"have":[3],"proven":[4],"to":[5,14,17,98,128,179],"be":[6,129],"a":[7,89,166],"powerful":[8],"tool":[9],"in":[10,21],"genomic":[11],"analysis":[12],"due":[13],"their":[15],"ability":[16],"encode":[18],"variations":[19],"found":[20],"multiple":[22],"haplotypes":[23,38,105],"and":[24,42,64,67,161,173],"capture":[25],"population":[26],"genetic":[27],"diversity.":[28],"Such":[29],"graphs":[30,85,144],"also":[31],"unavoidably":[32],"contain":[33,95],"paths":[34,58,96],"which":[35],"switch":[36],"between":[37],"(i.e.,":[39,106],"recombinant":[40,57],"paths)":[41,108],"thus":[43],"do":[44],"not":[45],"fully":[46],"match":[47],"any":[48],"of":[49,55,80,92,102,122,145],"the":[50,78,103,120,159],"constituent":[51],"haplotypes.":[52],"The":[53],"number":[54,121],"such":[56],"increases":[59],"combinatorially":[60],"with":[61,109],"path":[62],"length":[63],"cause":[65],"inefficiencies":[66],"false":[68],"positives":[69],"when":[70],"mapping":[71],"reads.":[72],"In":[73],"this":[74,115,164],"paper,":[75],"we":[76,133],"study":[77],"problem":[79,116],"finding":[81,140],"reduced":[82,142],"haplotype-aware":[83,141],"that":[86],"incorporate":[87],"only":[88],"selected":[90],"subset":[91],"variants,":[93],"yet":[94],"corresponding":[97],"all":[99],"\u03b1-long":[100],"substrings":[101],"input":[104],"non-recombinant":[107],"at":[110],"most":[111],"\u03b4":[112],"mismatches.":[113],"Solving":[114],"optimally,":[117],"i.e.,":[118],"minimizing":[119],"variants":[123],"selected,":[124],"is":[125,165],"previously":[126],"known":[127],"NP-hard":[130],"[14].":[131],"Here,":[132],"first":[134],"establish":[135],"several":[136],"inapproximability":[137],"results":[138],"regarding":[139],"variation":[143],"optimal":[146],"size.":[147],"We":[148],"then":[149],"present":[150],"an":[151],"integer":[152],"linear":[153],"programming":[154],"(ILP)":[155],"formulation":[156],"for":[157,170],"solving":[158],"problem,":[160],"experimentally":[162],"demonstrate":[163],"computationally":[167],"feasible":[168],"approach":[169],"real-world":[171],"problems":[172],"provides":[174],"far":[175],"superior":[176],"reduction":[177],"compared":[178],"prior":[180],"approaches.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}