{"id":"https://openalex.org/W2570372911","doi":"https://doi.org/10.1093/bioinformatics/btw832","title":"ntCard: a streaming algorithm for cardinality estimation in genomics data","display_name":"ntCard: a streaming algorithm for cardinality estimation in genomics data","publication_year":2017,"publication_date":"2017-01-05","ids":{"openalex":"https://openalex.org/W2570372911","doi":"https://doi.org/10.1093/bioinformatics/btw832","mag":"2570372911","pmid":"https://pubmed.ncbi.nlm.nih.gov/28453674"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btw832","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw832","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/9/1324/25151243/btw832.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/33/9/1324/25151243/btw832.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111786891","display_name":"Hamid Mohamadi","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hamid Mohamadi","raw_affiliation_strings":["Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada","Faculty of Science, University of British Columbia, Vancouver, BC, Canada","Canada's Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]},{"raw_affiliation_string":"Faculty of Science, University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Canada's Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056009314","display_name":"Hamza Khan","orcid":"https://orcid.org/0000-0002-0398-4848"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hamza Khan","raw_affiliation_strings":["Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada","Faculty of Science, University of British Columbia, Vancouver, BC, Canada","Canada's Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]},{"raw_affiliation_string":"Faculty of Science, University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Canada's Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017539699","display_name":"\u0130nan\u00e7 Birol","orcid":"https://orcid.org/0000-0003-0950-7839"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Inanc Birol","raw_affiliation_strings":["Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada","Faculty of Science, University of British Columbia, Vancouver, BC, Canada","Canada's Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canada\u2019s Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]},{"raw_affiliation_string":"Faculty of Science, University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Canada's Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017539699","https://openalex.org/A5111786891"],"corresponding_institution_ids":["https://openalex.org/I141945490","https://openalex.org/I4210133112"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.8257,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.94295389,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"33","issue":"9","first_page":"1324","last_page":"1330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8705000281333923,"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":0.8705000281333923,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.0786999985575676,"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/T11269","display_name":"Algorithms and Data Compression","score":0.014600000344216824,"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/k-mer","display_name":"k-mer","score":0.6624158620834351},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5967907309532166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5892682075500488},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5081062316894531},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.49666959047317505},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.48775964975357056},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.45724985003471375},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4221475124359131},{"id":"https://openalex.org/keywords/shotgun-sequencing","display_name":"Shotgun sequencing","score":0.41702800989151},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.41360968351364136},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.41324102878570557},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.4105035662651062},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.32829198241233826},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.29948604106903076},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.165725976228714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13936147093772888}],"concepts":[{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.6624158620834351},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5967907309532166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5892682075500488},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5081062316894531},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.49666959047317505},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.48775964975357056},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.45724985003471375},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4221475124359131},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.41702800989151},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.41360968351364136},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.41324102878570557},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.4105035662651062},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.32829198241233826},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29948604106903076},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.165725976228714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13936147093772888},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","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":"D018745","descriptor_name":"Genome, Plant","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018745","descriptor_name":"Genome, Plant","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018745","descriptor_name":"Genome, Plant","qualifier_ui":null,"qualifier_name":null,"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":"D028222","descriptor_name":"Picea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D028222","descriptor_name":"Picea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D028222","descriptor_name":"Picea","qualifier_ui":"Q000235","qualifier_name":"genetics","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":3,"locations":[{"id":"doi:10.1093/bioinformatics/btw832","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw832","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/9/1324/25151243/btw832.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:28453674","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28453674","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},{"id":"pmh:oai:pubmedcentral.nih.gov:5408799","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5408799","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btw832","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw832","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/9/1324/25151243/btw832.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4969115678","display_name":null,"funder_award_id":"R01 HG007182","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G6277516419","display_name":null,"funder_award_id":"R01HG007182","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320310787","display_name":"Genome Canada","ror":"https://ror.org/029s29983"},{"id":"https://openalex.org/F4320319973","display_name":"Genome British Columbia","ror":"https://ror.org/03gne5057"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320335036","display_name":"BC Cancer Agency","ror":"https://ror.org/03sfybe47"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1785933978","https://openalex.org/W1966822396","https://openalex.org/W2025051251","https://openalex.org/W2057253402","https://openalex.org/W2065128082","https://openalex.org/W2069414131","https://openalex.org/W2080234606","https://openalex.org/W2080745194","https://openalex.org/W2096128575","https://openalex.org/W2104677379","https://openalex.org/W2107443258","https://openalex.org/W2121530737","https://openalex.org/W2125266506","https://openalex.org/W2127768708","https://openalex.org/W2132926880","https://openalex.org/W2133531097","https://openalex.org/W2142749416","https://openalex.org/W2148425737","https://openalex.org/W2160265768","https://openalex.org/W2160969485","https://openalex.org/W2161546116","https://openalex.org/W2163584430","https://openalex.org/W2168546919","https://openalex.org/W2168645015","https://openalex.org/W2410272654","https://openalex.org/W2422772473","https://openalex.org/W2463091895","https://openalex.org/W2515342656","https://openalex.org/W2589379462","https://openalex.org/W2952870794","https://openalex.org/W2952932047","https://openalex.org/W2953202204","https://openalex.org/W6734232148"],"related_works":["https://openalex.org/W1527507758","https://openalex.org/W2166654698","https://openalex.org/W2157460239","https://openalex.org/W2166973401","https://openalex.org/W2213265806","https://openalex.org/W2165847428","https://openalex.org/W2010454899","https://openalex.org/W2008090296","https://openalex.org/W2006192792","https://openalex.org/W2047803783"],"abstract_inverted_index":{"Motivation:":[0],"Many":[1],"bioinformatics":[2],"algorithms":[3],"are":[4,288],"designed":[5],"for":[6,57,85,112,135,254],"the":[7,37,114,127,141,153,164,168,174,198,208,212,216,231,271],"analysis":[8,63,86],"of":[9,11,39,50,97,116,176,187,237],"sequences":[10],"some":[12],"uniform":[13],"length,":[14],"conventionally":[15],"referred":[16],"to":[17,35,46,73,130,145,162],"as":[18,249],"k":[19,41,51,91,117,224],"-mers.":[20],"These":[21],"include":[22],"de":[23],"Bruijn":[24],"graph":[25],"assembly":[26],"methods":[27],"and":[28,60,81,178,192,211,239,259,267],"sequence":[29],"alignment":[30],"tools.":[31,87],"An":[32],"efficient":[33],"algorithm":[34,111,129],"enumerate":[36],"number":[38],"unique":[40],"-mers,":[42],"or":[43,282],"even":[44],"better,":[45],"build":[47,146],"a":[48,90,101,109,147,159,250],"histogram":[49,93],"-mer":[52,92,225],"frequencies":[53,69,115,227],"would":[54],"be":[55,71],"desirable":[56],"these":[58],"tools":[59],"their":[61],"downstream":[62],"pipelines.":[64],"Among":[65],"other":[66,179],"applications,":[67],"estimated":[68],"can":[70],"used":[72,184],"predict":[74],"genome":[75,203,210],"sizes,":[76],"measure":[77],"sequencing":[78,98,205],"error":[79],"rates,":[80],"tune":[82],"runtime":[83],"parameters":[84],"However,":[88],"calculating":[89],"from":[94,167],"large":[95],"volumes":[96],"data":[99,287],"is":[100,262,268,275],"challenging":[102],"task.":[103],"Results:":[104],"Here,":[105],"we":[106],"present":[107],"ntCard,":[108],"streaming":[110],"estimating":[113],"-mers":[118],"in":[119,195,264],"genomics":[120,256],"datasets.":[121],"At":[122],"its":[123],"core,":[124],"ntCard":[125,177,222,248,261],"uses":[126,158],"ntHash":[128],"efficiently":[131],"compute":[132],"hash":[133,143],"values":[134,144],"streamed":[136],"sequences.":[137],"It":[138,274],"then":[139],"samples":[140],"calculated":[142],"reduced":[148],"representation":[149],"multiplicity":[150],"table":[151],"describing":[152],"sample":[154,169],"distribution.":[155,170],"Finally,":[156],"it":[157],"statistical":[160],"model":[161],"reconstruct":[163],"population":[165],"distribution":[166],"We":[171,183],"have":[172],"compared":[173],"performance":[175],"cardinality":[180],"estimation":[181],"algorithms.":[182],"three":[185],"datasets":[186],"480":[188],"GB,":[189],"500":[190],"GB":[191],"2.4":[193],"TB":[194],"size,":[196],"where":[197],"first":[199],"two":[200],"representing":[201],"whole":[202],"shotgun":[204],"experiments":[206],"on":[207,215],"human":[209],"last":[213],"one":[214],"white":[217],"spruce":[218],"genome.":[219],"Results":[220],"show":[221],"estimates":[223],"coverage":[226],">15\u00d7":[228],"faster":[229],"than":[230],"state-of-the-art":[232],"algorithms,":[233],"using":[234],"similar":[235],"amount":[236],"memory,":[238],"with":[240],"higher":[241],"accuracy":[242],"rates.":[243],"Thus,":[244],"our":[245],"benchmarks":[246],"demonstrate":[247],"potentially":[251],"enabling":[252],"technology":[253],"large-scale":[255],"applications.":[257],"Availability":[258],"Implementation:":[260],"written":[263],"C":[265],"++":[266],"released":[269],"under":[270],"GPL":[272],"license.":[273],"freely":[276],"available":[277,289],"at":[278,290],"https://github.com/bcgsc/ntCard.":[279],"Contact:":[280],"hmohamadi@bcgsc.ca":[281],"ibirol@bcgsc.ca.":[283],"Supplementary":[284,286],"information:":[285],"Bioinformatics":[291],"online.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}