{"id":"https://openalex.org/W2952932047","doi":"https://doi.org/10.1093/bioinformatics/btu713","title":"KmerStream: streaming algorithms for <i>k</i> -mer abundance estimation","display_name":"KmerStream: streaming algorithms for <i>k</i> -mer abundance estimation","publication_year":2014,"publication_date":"2014-10-28","ids":{"openalex":"https://openalex.org/W2952932047","doi":"https://doi.org/10.1093/bioinformatics/btu713","mag":"2952932047","pmid":"https://pubmed.ncbi.nlm.nih.gov/25355787"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu713","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu713","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/24/3541/48931408/bioinformatics_30_24_3541.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/30/24/3541/48931408/bioinformatics_30_24_3541.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018556494","display_name":"P\u00e1ll Melsted","orcid":"https://orcid.org/0000-0002-8418-6724"},"institutions":[{"id":"https://openalex.org/I1327191685","display_name":"deCODE Genetics (Iceland)","ror":"https://ror.org/04dzdm737","country_code":"IS","type":"company","lineage":["https://openalex.org/I1327191685"]},{"id":"https://openalex.org/I123185442","display_name":"Reykjav\u00edk University","ror":"https://ror.org/05d2kyx68","country_code":"IS","type":"education","lineage":["https://openalex.org/I123185442"]},{"id":"https://openalex.org/I165368041","display_name":"University of Iceland","ror":"https://ror.org/01db6h964","country_code":"IS","type":"education","lineage":["https://openalex.org/I165368041"]}],"countries":["IS"],"is_corresponding":true,"raw_author_name":"P\u00e1ll Melsted","raw_affiliation_strings":["1 Faculty of Industrial Engineering, Mechanical Engineering and Computer Science, University of Iceland, Reykjav\u00edk, Iceland, 2 deCODE Genetics/Amgen, Reykjav\u00edk, Iceland and 3 School of Science and Engineering, Reykjav\u00edk University, Reykjav\u00edk, Iceland"],"affiliations":[{"raw_affiliation_string":"1 Faculty of Industrial Engineering, Mechanical Engineering and Computer Science, University of Iceland, Reykjav\u00edk, Iceland, 2 deCODE Genetics/Amgen, Reykjav\u00edk, Iceland and 3 School of Science and Engineering, Reykjav\u00edk University, Reykjav\u00edk, Iceland","institution_ids":["https://openalex.org/I1327191685","https://openalex.org/I123185442","https://openalex.org/I165368041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004725925","display_name":"Bjarni V. Halld\u00f3rsson","orcid":"https://orcid.org/0000-0003-0756-0767"},"institutions":[{"id":"https://openalex.org/I1327191685","display_name":"deCODE Genetics (Iceland)","ror":"https://ror.org/04dzdm737","country_code":"IS","type":"company","lineage":["https://openalex.org/I1327191685"]},{"id":"https://openalex.org/I165368041","display_name":"University of Iceland","ror":"https://ror.org/01db6h964","country_code":"IS","type":"education","lineage":["https://openalex.org/I165368041"]},{"id":"https://openalex.org/I123185442","display_name":"Reykjav\u00edk University","ror":"https://ror.org/05d2kyx68","country_code":"IS","type":"education","lineage":["https://openalex.org/I123185442"]}],"countries":["IS"],"is_corresponding":false,"raw_author_name":"Bjarni V. Halld\u00f3rsson","raw_affiliation_strings":["1 Faculty of Industrial Engineering, Mechanical Engineering and Computer Science, University of Iceland, Reykjav\u00edk, Iceland, 2 deCODE Genetics/Amgen, Reykjav\u00edk, Iceland and 3 School of Science and Engineering, Reykjav\u00edk University, Reykjav\u00edk, Iceland"],"affiliations":[{"raw_affiliation_string":"1 Faculty of Industrial Engineering, Mechanical Engineering and Computer Science, University of Iceland, Reykjav\u00edk, Iceland, 2 deCODE Genetics/Amgen, Reykjav\u00edk, Iceland and 3 School of Science and Engineering, Reykjav\u00edk University, Reykjav\u00edk, Iceland","institution_ids":["https://openalex.org/I1327191685","https://openalex.org/I123185442","https://openalex.org/I165368041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018556494"],"corresponding_institution_ids":["https://openalex.org/I123185442","https://openalex.org/I1327191685","https://openalex.org/I165368041"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.5596,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.90243809,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"30","issue":"24","first_page":"3541","last_page":"3547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9973999857902527,"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.9818999767303467,"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/k-mer","display_name":"k-mer","score":0.7346513867378235},{"id":"https://openalex.org/keywords/streaming-algorithm","display_name":"Streaming algorithm","score":0.61025071144104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6069669723510742},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.5875498056411743},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5749124884605408},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5585525035858154},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.45574191212654114},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.4281330108642578},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.42144346237182617},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40266573429107666},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.362482488155365},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.36156222224235535},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3240041136741638},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22603216767311096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21685755252838135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1474936306476593},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11422118544578552},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.09243673086166382}],"concepts":[{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.7346513867378235},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.61025071144104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6069669723510742},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.5875498056411743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5749124884605408},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5585525035858154},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.45574191212654114},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.4281330108642578},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.42144346237182617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40266573429107666},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.362482488155365},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.36156222224235535},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3240041136741638},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22603216767311096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21685755252838135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1474936306476593},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11422118544578552},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.09243673086166382},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"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":"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":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","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":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":"D017422","descriptor_name":"Sequence Analysis, DNA","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},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059646","descriptor_name":"Genome Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059646","descriptor_name":"Genome Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059646","descriptor_name":"Genome Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btu713","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu713","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/24/3541/48931408/bioinformatics_30_24_3541.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:25355787","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25355787","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/btu713","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu713","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/24/3541/48931408/bioinformatics_30_24_3541.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952932047.pdf","grobid_xml":"https://content.openalex.org/works/W2952932047.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1785933978","https://openalex.org/W1990139627","https://openalex.org/W2014099509","https://openalex.org/W2022986961","https://openalex.org/W2025051251","https://openalex.org/W2025583382","https://openalex.org/W2027667941","https://openalex.org/W2036521197","https://openalex.org/W2037444377","https://openalex.org/W2064379477","https://openalex.org/W2096128575","https://openalex.org/W2097066660","https://openalex.org/W2104045630","https://openalex.org/W2104677379","https://openalex.org/W2108058966","https://openalex.org/W2115038037","https://openalex.org/W2119180969","https://openalex.org/W2127768708","https://openalex.org/W2133531097","https://openalex.org/W2133956160","https://openalex.org/W2149118757","https://openalex.org/W2152246890","https://openalex.org/W2160834953","https://openalex.org/W2160969485","https://openalex.org/W2161546116","https://openalex.org/W2163584430","https://openalex.org/W2163830511","https://openalex.org/W2166859993","https://openalex.org/W2168133698","https://openalex.org/W2179933869","https://openalex.org/W6647979485"],"related_works":["https://openalex.org/W2411730464","https://openalex.org/W2188499136","https://openalex.org/W2922326376","https://openalex.org/W2950956043","https://openalex.org/W4388228158","https://openalex.org/W2607704574","https://openalex.org/W2368818187","https://openalex.org/W2751607437","https://openalex.org/W153132339","https://openalex.org/W2067283583"],"abstract_inverted_index":{"We":[0,42,93,118],"present":[1,13],"KmerStream,":[2],"a":[3,44,89,97,130],"streaming":[4],"algorithm":[5,19],"for":[6,149],"estimating":[7],"the":[8,25,28,31,37,40,52,56,62,67,85,107,115,122,140],"number":[9],"of":[10,27,39,55,88,99,132],"distinct":[11],"k-mers":[12],"in":[14,21,24,36,139],"high-throughput":[15],"sequencing":[16,57,91,116,144],"data.":[17],"The":[18],"runs":[20],"time":[22],"linear":[23],"size":[26,38],"input":[29],"and":[30,105],"space":[32],"requirement":[33],"are":[34,126],"logarithmic":[35],"input.":[41],"derive":[43],"simple":[45],"model":[46],"that":[47,120],"allows":[48],"us":[49],"to":[50,83,110],"estimate":[51],"error":[53,86,108,133,141],"rate":[54,87,109],"experiment,":[58],"as":[59,61,129],"well":[60],"genome":[63,102],"size,":[64],"using":[65],"only":[66],"aggregate":[68],"statistics":[69],"reported":[70,113,150],"by":[71,114],"KmerStream.":[72],"As":[73],"an":[74],"application":[75],"we":[76],"show":[77],"how":[78],"KmerStream":[79,95],"can":[80],"be":[81],"used":[82],"compute":[84],"DNA":[90],"experiment.":[92],"run":[94],"on":[96],"set":[98],"2656":[100],"whole":[101],"sequenced":[103],"individuals":[104],"compare":[106],"quality":[111,123,151],"values":[112,124],"equipment.":[117],"discover":[119],"while":[121],"alone":[125],"largely":[127],"reliable":[128],"predictor":[131],"rate,":[134],"there":[135],"is":[136],"considerable":[137],"variability":[138],"rates":[142],"between":[143],"runs,":[145],"even":[146],"when":[147],"accounting":[148],"values.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2019-06-27T00:00:00"}
