{"id":"https://openalex.org/W4221076494","doi":"https://doi.org/10.1186/s13015-022-00212-0","title":"Space-efficient representation of genomic k-mer count tables","display_name":"Space-efficient representation of genomic k-mer count tables","publication_year":2022,"publication_date":"2022-03-21","ids":{"openalex":"https://openalex.org/W4221076494","doi":"https://doi.org/10.1186/s13015-022-00212-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/35317833"},"language":"en","primary_location":{"id":"doi:10.1186/s13015-022-00212-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-022-00212-0","pdf_url":"https://almob.biomedcentral.com/track/pdf/10.1186/s13015-022-00212-0","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/track/pdf/10.1186/s13015-022-00212-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046831374","display_name":"Yoshihiro Shibuya","orcid":"https://orcid.org/0000-0002-3137-1504"},"institutions":[{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]},{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yoshihiro Shibuya","raw_affiliation_strings":["LIGM, Universit\u00e9 Gustave Eiffel, Marne-la-Vall\u00e9e, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIGM, Universit\u00e9 Gustave Eiffel, Marne-la-Vall\u00e9e, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I4210154111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059502958","display_name":"Djamal Belazzougui","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095777","display_name":"Centre de Recherche sur l'Information Scientifique et Technique","ror":"https://ror.org/01k1bte55","country_code":"DZ","type":"government","lineage":["https://openalex.org/I4210095777","https://openalex.org/I4210114810"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Djamal Belazzougui","raw_affiliation_strings":["CAPA, DTISI, Centre de Recherche sur l'Information Scientifique et Technique, Algiers, DZ, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAPA, DTISI, Centre de Recherche sur l'Information Scientifique et Technique, Algiers, DZ, Algeria","institution_ids":["https://openalex.org/I4210095777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012626407","display_name":"Gr\u00e9gory Kucherov","orcid":"https://orcid.org/0000-0001-5899-5424"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Gregory Kucherov","raw_affiliation_strings":["LIGM, Universit\u00e9 Gustave Eiffel, Marne-la-Vall\u00e9e, France. gregory.kucherov@univ-eiffel.fr","Skolkovo Institute of Science and Technology, Moscow, Russia. gregory.kucherov@univ-eiffel.fr","Skolkovo Institute of Science and Technology, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIGM, Universit\u00e9 Gustave Eiffel, Marne-la-Vall\u00e9e, France. gregory.kucherov@univ-eiffel.fr","institution_ids":[]},{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia. gregory.kucherov@univ-eiffel.fr","institution_ids":[]},{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russia","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012626407"],"corresponding_institution_ids":["https://openalex.org/I125989756"],"apc_list":{"value":1490,"currency":"GBP","value_usd":1827},"apc_paid":{"value":1490,"currency":"GBP","value_usd":1827},"fwci":0.8667,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.70474027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"17","issue":"1","first_page":"5","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994000196456909,"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":0.9994000196456909,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.996399998664856,"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":0.9962000250816345,"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/bloom-filter","display_name":"Bloom filter","score":0.823169469833374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6957088708877563},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.6639739274978638},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5136367678642273},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4642854928970337},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.45840907096862793},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.4223080277442932},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.3425339460372925},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28928661346435547},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13466861844062805},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11718776822090149}],"concepts":[{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.823169469833374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6957088708877563},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.6639739274978638},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5136367678642273},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4642854928970337},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.45840907096862793},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.4223080277442932},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.3425339460372925},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28928661346435547},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13466861844062805},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11718776822090149},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13015-022-00212-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-022-00212-0","pdf_url":"https://almob.biomedcentral.com/track/pdf/10.1186/s13015-022-00212-0","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:35317833","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35317833","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":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:HAL:hal-03867526v1","is_oa":true,"landing_page_url":"https://cnrs.hal.science/hal-03867526","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, 2022, 17 (1), pp.5. &#x27E8;10.1186/s13015-022-00212-0&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:112aac36a8ed4c1f98d21989a6b535f2","is_oa":false,"landing_page_url":"https://doaj.org/article/112aac36a8ed4c1f98d21989a6b535f2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, Vol 17, Iss 1, Pp 1-15 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8939220","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8939220","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms Mol Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13015-022-00212-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-022-00212-0","pdf_url":"https://almob.biomedcentral.com/track/pdf/10.1186/s13015-022-00212-0","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221076494.pdf","grobid_xml":"https://content.openalex.org/works/W4221076494.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1533146036","https://openalex.org/W1634257591","https://openalex.org/W1797602580","https://openalex.org/W1998262268","https://openalex.org/W2006075770","https://openalex.org/W2057253402","https://openalex.org/W2096128575","https://openalex.org/W2097160089","https://openalex.org/W2111295912","https://openalex.org/W2132069633","https://openalex.org/W2144560237","https://openalex.org/W2150774511","https://openalex.org/W2159954944","https://openalex.org/W2194172909","https://openalex.org/W2198888083","https://openalex.org/W2583363792","https://openalex.org/W2784311175","https://openalex.org/W2788348538","https://openalex.org/W2789843538","https://openalex.org/W2891646971","https://openalex.org/W2920035183","https://openalex.org/W2952363540","https://openalex.org/W2953339515","https://openalex.org/W2998284004","https://openalex.org/W2999307977","https://openalex.org/W3016701095","https://openalex.org/W3023465514","https://openalex.org/W3043153155","https://openalex.org/W3081159514","https://openalex.org/W3090493712","https://openalex.org/W3117679888","https://openalex.org/W3121458864","https://openalex.org/W3131575902","https://openalex.org/W3132474731","https://openalex.org/W3134981461","https://openalex.org/W4254982796","https://openalex.org/W6947873881"],"related_works":["https://openalex.org/W2086572746","https://openalex.org/W2604468458","https://openalex.org/W2157216338","https://openalex.org/W2563930566","https://openalex.org/W4226101760","https://openalex.org/W2417068752","https://openalex.org/W3132474731","https://openalex.org/W2097066660","https://openalex.org/W4297832806","https://openalex.org/W2950790201"],"abstract_inverted_index":{"MOTIVATION:":[0],"k-mer":[1,22,56,89,168,186],"counting":[2],"is":[3],"a":[4,104,110,114,118,205],"common":[5],"task":[6],"in":[7,20,44,91],"bioinformatic":[8],"pipelines,":[9],"with":[10,71,130],"many":[11],"dedicated":[12],"tools":[13,18],"available.":[14],"Many":[15],"of":[16,33,55,79,88,99,133,171,198,207,210],"these":[17,153,165],"produce":[19],"output":[21],"count":[23,57,169],"tables":[24,37,58,170,189],"containing":[25],"both":[26],"k-mers":[27],"and":[28,176,179],"counts,":[29,200],"easily":[30],"reaching":[31],"tens":[32],"GB.":[34],"Furthermore,":[35,126],"such":[36],"do":[38],"not":[39,102],"support":[40],"efficient":[41,53],"random-access":[42,61],"queries":[43],"general.":[45],"RESULTS:":[46],"In":[47,195],"this":[48,124],"work,":[49],"we":[50,116,135],"design":[51],"an":[52],"representation":[54,202],"supporting":[59],"fast":[60],"queries.":[62],"We":[63,150,162],"propose":[64],"to":[65,74,113,155],"apply":[66],"Compressed":[67],"Static":[68],"Functions":[69],"(CSFs),":[70],"space":[72,209],"proportional":[73],"the":[75,80,94,141,156,196,208,211],"empirical":[76,142,212],"zero-order":[77],"entropy":[78,143],"counts.":[81],"For":[82],"very":[83],"skewed":[84],"distributions,":[85],"like":[86],"those":[87],"counts":[90],"whole":[92,172],"genomes,":[93],"only":[95],"currently":[96],"available":[97],"implementation":[98],"CSFs":[100],"does":[101],"provide":[103],"compact":[105],"enough":[106,148,216],"representation.":[107],"By":[108],"adding":[109],"Bloom":[111],"filter":[112],"CSF":[115,120],"obtain":[117],"Bloom-enhanced":[119],"(BCSF)":[121],"effectively":[122],"overcoming":[123],"limitation.":[125],"by":[127],"combining":[128],"BCSFs":[129],"minimizer-based":[131],"bucketing":[132],"k-mers,":[134],"build":[136],"even":[137],"smaller":[138],"representations":[139,154],"breaking":[140],"lower":[144],"bound,":[145],"for":[146,190,214],"large":[147,215],"k.":[149],"also":[151],"extend":[152],"approximate":[157],"case,":[158],"gaining":[159],"additional":[160],"space.":[161],"experimentally":[163],"validate":[164],"techniques":[166],"on":[167,185],"genomes":[173],"(E.":[174],"Coli":[175,193],"C.":[177],"Elegans)":[178],"unassembled":[180],"reads,":[181],"as":[182,184],"well":[183],"document":[187],"frequency":[188],"29":[191],"E.":[192],"genomes.":[194],"case":[197],"exact":[199],"our":[201],"takes":[203],"about":[204],"half":[206],"entropy,":[213],"k's.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
