{"id":"https://openalex.org/W3046491233","doi":"https://doi.org/10.1109/ipdpsw50202.2020.00041","title":"Kcollections: A Fast and Efficient Library for K-mers","display_name":"Kcollections: A Fast and Efficient Library for K-mers","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3046491233","doi":"https://doi.org/10.1109/ipdpsw50202.2020.00041","mag":"3046491233"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw50202.2020.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw50202.2020.00041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063608648","display_name":"Mao Fujimoto","orcid":"https://orcid.org/0000-0002-2020-935X"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. Stanley Fujimoto","raw_affiliation_strings":["Computer Science Department, Brigham Young University, Provo, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University, Provo, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052915205","display_name":"Cole A. Lyman","orcid":"https://orcid.org/0000-0001-7921-165X"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cole A. Lyman","raw_affiliation_strings":["Computer Science Department, Brigham Young University, Provo, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University, Provo, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058435710","display_name":"Mark Clement","orcid":"https://orcid.org/0000-0003-4902-3521"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark J. Clement","raw_affiliation_strings":["Computer Science Department, Brigham Young University, Provo, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University, Provo, USA","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063608648"],"corresponding_institution_ids":["https://openalex.org/I100005738"],"apc_list":null,"apc_paid":null,"fwci":0.0829,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44055052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9984999895095825,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770740270614624},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7149696350097656},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.6652782559394836},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6207513809204102},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.48066508769989014},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.47510847449302673},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4535922706127167},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4506542682647705},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36248579621315},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3406674563884735},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.2429836392402649},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2242869734764099},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.1863088309764862},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17411893606185913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16136732697486877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770740270614624},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7149696350097656},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.6652782559394836},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6207513809204102},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.48066508769989014},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47510847449302673},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4535922706127167},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4506542682647705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36248579621315},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3406674563884735},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2429836392402649},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2242869734764099},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.1863088309764862},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17411893606185913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16136732697486877},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw50202.2020.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw50202.2020.00041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1993695973","https://openalex.org/W2005202728","https://openalex.org/W2076747312","https://openalex.org/W2096128575","https://openalex.org/W2278452282","https://openalex.org/W2761301729","https://openalex.org/W2805745445","https://openalex.org/W2809649683","https://openalex.org/W2884435343","https://openalex.org/W2949074212","https://openalex.org/W2950354111","https://openalex.org/W4247053599","https://openalex.org/W6745064620"],"related_works":["https://openalex.org/W2120956621","https://openalex.org/W2915362964","https://openalex.org/W2340761128","https://openalex.org/W2950309954","https://openalex.org/W3205360317","https://openalex.org/W3215786367","https://openalex.org/W4399205235","https://openalex.org/W3200242814","https://openalex.org/W4214573178","https://openalex.org/W4282946044"],"abstract_inverted_index":{"K-mers":[0],"form":[1],"the":[2,18,139],"backbone":[3],"of":[4,20,33,111,142],"many":[5],"bioinformatic":[6,133],"algorithms.":[7],"They":[8],"are,":[9],"however,":[10],"difficult":[11],"to":[12],"store":[13],"and":[14,80,97],"use":[15],"efficiently":[16],"because":[17],"number":[19],"k-mers":[21,58,86],"increases":[22],"exponentially":[23],"as":[24,60,102,104],"k":[25],"increases.":[26],"Many":[27],"algorithms":[28,134],"exist":[29],"for":[30,85,95,127],"compressed":[31,79],"storage":[32],"kmers":[34],"but":[35],"suffer":[36],"from":[37,88],"slow":[38],"insert":[39],"times":[40],"or":[41,68],"are":[42],"probabilistic":[43],"resulting":[44],"in":[45,53,63],"false-positive":[46],"k-mers.":[47,144],"Furthermore,":[48],"k-mer":[49,69,106],"libraries":[50],"usually":[51],"specialize":[52],"associating":[54],"specific":[55],"values":[56],"with":[57],"such":[59],"a":[61,78,105,118],"color":[62],"colored":[64],"de":[65],"Bruijn":[66],"Graphs":[67],"count.":[70],"We":[71],"present":[72],"kcollections":[73],"<sup":[74],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[75],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[76],",":[77],"parallel":[81,114],"data":[82,108],"structure":[83,109],"designed":[84,116],"generated":[87],"whole,":[89],"assembled":[90],"genomes.":[91],"Kcollections":[92,130],"is":[93],"available":[94],"C++":[96],"provides":[98],"set-and":[99],"maplike":[100],"structures":[101],"well":[103],"counting":[107],"all":[110],"which":[112],"utilize":[113],"operations":[115],"using":[117],"MapReduce":[119],"paradigm.":[120],"Additionally,":[121],"we":[122],"provide":[123],"basic":[124],"Python":[125],"bindings":[126],"rapid":[128],"prototyping.":[129],"makes":[131],"developing":[132],"simpler":[135],"by":[136],"abstracting":[137],"away":[138],"tedious":[140],"task":[141],"storing":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}