{"id":"https://openalex.org/W2973021521","doi":"https://doi.org/10.1145/3307339.3342144","title":"Practical Universal k-mer Sets for Minimizer Schemes","display_name":"Practical Universal k-mer Sets for Minimizer Schemes","publication_year":2019,"publication_date":"2019-09-04","ids":{"openalex":"https://openalex.org/W2973021521","doi":"https://doi.org/10.1145/3307339.3342144","mag":"2973021521"},"language":"en","primary_location":{"id":"doi:10.1145/3307339.3342144","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3307339.3342144","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3307339.3342144","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 10th 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/10.1145/3307339.3342144","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014004628","display_name":"Dan DeBlasio","orcid":"https://orcid.org/0000-0003-4110-4431"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan DeBlasio","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066016740","display_name":"Fiyinfoluwa Gbosibo","orcid":null},"institutions":[{"id":"https://openalex.org/I33821262","display_name":"Lincoln University - Pennsylvania","ror":"https://ror.org/0521rfb23","country_code":"US","type":"education","lineage":["https://openalex.org/I33821262"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fiyinfoluwa Gbosibo","raw_affiliation_strings":["Lincoln University, Lincoln, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lincoln University, Lincoln, PA, USA","institution_ids":["https://openalex.org/I33821262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113653378","display_name":"Carl Kingsford","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Kingsford","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009407234","display_name":"Guillaume Mar\u00e7ais","orcid":"https://orcid.org/0000-0002-5083-5925"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guillaume Mar\u00e7ais","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1693,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.90750211,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9944000244140625,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9944000244140625,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9933000206947327,"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":0.9901000261306763,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lexicographical-order","display_name":"Lexicographical order","score":0.6082196235656738},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.591804563999176},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5072004795074463},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5016944408416748},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.5002613067626953},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4896555542945862},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4822145700454712},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44908732175827026},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.42285582423210144},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3867376744747162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.37208735942840576},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07795748114585876}],"concepts":[{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.6082196235656738},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.591804563999176},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5072004795074463},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5016944408416748},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.5002613067626953},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4896555542945862},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4822145700454712},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44908732175827026},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.42285582423210144},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3867376744747162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37208735942840576},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07795748114585876},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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:10.1145/3307339.3342144","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3307339.3342144","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3307339.3342144","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 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3307339.3342144","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3307339.3342144","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3307339.3342144","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 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1325684988","display_name":null,"funder_award_id":"CCF-1256087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1696008617","display_name":null,"funder_award_id":"CCF-1319998, CCF-1256087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2933222473","display_name":"AF: Small: Multiscale Spectral Signatures for Local and Multi-objective Biological Network Alignment","funder_award_id":"1319998","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3023850491","display_name":null,"funder_award_id":"R01GM122935","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3355402586","display_name":"Carl Kingsford Investigator Award","funder_award_id":"GBMF4554","funder_id":"https://openalex.org/F4320306202","funder_display_name":"Gordon and Betty Moore Foundation"},{"id":"https://openalex.org/G3641969089","display_name":"CAREER: Model-based Reconstruction of Ancient Biological Networks","funder_award_id":"1256087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7958957864","display_name":null,"funder_award_id":"CCF-1256087, CCF-1319998","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"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320310174","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2973021521.pdf","grobid_xml":"https://content.openalex.org/works/W2973021521.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1971100822","https://openalex.org/W2009119978","https://openalex.org/W2010454899","https://openalex.org/W2016995838","https://openalex.org/W2102841127","https://openalex.org/W2111295912","https://openalex.org/W2111307596","https://openalex.org/W2125266506","https://openalex.org/W2144560237","https://openalex.org/W2159954944","https://openalex.org/W2194172909","https://openalex.org/W2438121987","https://openalex.org/W2487384794","https://openalex.org/W2587288030","https://openalex.org/W2592570088","https://openalex.org/W2597444305","https://openalex.org/W2763390627","https://openalex.org/W2937044610","https://openalex.org/W2950150251","https://openalex.org/W2950572599","https://openalex.org/W2951822379","https://openalex.org/W2952609831","https://openalex.org/W2953263404","https://openalex.org/W3102863871"],"related_works":["https://openalex.org/W1993634787","https://openalex.org/W3125614403","https://openalex.org/W2476923378","https://openalex.org/W2803221307","https://openalex.org/W2951826204","https://openalex.org/W4211001408","https://openalex.org/W2024334686","https://openalex.org/W3144842310","https://openalex.org/W2128940747","https://openalex.org/W2206006039"],"abstract_inverted_index":{"Minimizer":[0],"schemes":[1,25,59],"have":[2],"found":[3],"widespread":[4],"use":[5,26,63],"in":[6,109,123,130,139,169,197],"genomic":[7],"applications":[8],"as":[9,95],"a":[10,170,198],"way":[11,52],"to":[12,30,53,76,148,188],"quickly":[13],"predict":[14],"the":[15,49,62,84,110,113,124,136,167,176,191,205,212],"matching":[16],"probability":[17],"of":[18,33,64,71,112,126,135,155,166,175,193,207],"large":[19,153],"sequences.":[20],"Most":[21],"methods":[22,101],"for":[23,57,102,152],"minimizer":[24,58,150],"randomized":[27],"(or":[28],"close":[29],"randomized)":[31],"ordering":[32],"k-mers":[34,72,168],"when":[35],"finding":[36],"minimizers,":[37],"but":[38],"recent":[39],"work":[40],"has":[41],"shown":[42],"that":[43,73,115,144,157,182],"not":[44],"all":[45,78],"non-lexicographic":[46],"orderings":[47,56],"perform":[48],"same.":[50],"One":[51],"find":[54],"k-mer":[55,66,105,114,142],"is":[60],"through":[61],"universal":[65,104,141],"sets,":[67],"which":[68],"are":[69,74,93,98,107,158],"subsets":[70],"guaranteed":[75,187],"cover":[77],"windows.":[79],"The":[80],"smaller":[81],"this":[82,162,183],"set":[83,177],"fewer":[85],"false":[86,208],"positives":[87,209],"(where":[88],"two":[89],"poorly":[90],"aligned":[91],"sequences":[92],"labeled":[94],"possible":[96],"matches)":[97],"identified.":[99],"Current":[100],"creating":[103,140],"sets":[106,122,143,214],"limited":[108],"length":[111],"can":[116,145,202],"be":[117,146,186],"considered,":[118],"and":[119,172,200],"cannot":[120],"compute":[121],"range":[125],"lengths":[127],"currently":[128],"used":[129,147],"practice.":[131],"We":[132,160,179],"take":[133],"some":[134],"first":[137],"steps":[138],"construct":[149],"orders":[151],"values":[154],"k":[156],"practical.":[159],"do":[161],"using":[163,211],"iterative":[164],"extension":[165],"set,":[171],"guided":[173],"contraction":[174],"itself.":[178],"also":[180],"show":[181],"process":[184],"will":[185],"never":[189],"increase":[190],"number":[192,206],"distinct":[194],"minimizers":[195],"chosen":[196],"sequence,":[199],"thus":[201],"only":[203],"decrease":[204],"over":[210],"current":[213],"on":[215],"small":[216],"k-mers.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}