{"id":"https://openalex.org/W2981210020","doi":"https://doi.org/10.1142/s0219720019400110","title":"Indexing<i>k</i>-mers in linear space for quality value compression","display_name":"Indexing<i>k</i>-mers in linear space for quality value compression","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2981210020","doi":"https://doi.org/10.1142/s0219720019400110","mag":"2981210020","pmid":"https://pubmed.ncbi.nlm.nih.gov/31856669"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720019400110","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720019400110","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5046831374","display_name":"Yoshihiro Shibuya","orcid":"https://orcid.org/0000-0002-3137-1504"},"institutions":[{"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"]},{"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/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["FR","IT"],"is_corresponding":false,"raw_author_name":"Yoshihiro Shibuya","raw_affiliation_strings":["Department of Information Engineering, University of Padua, via Gradenigo 6B, Padua, Italy","Laboratoire d\u2019Informatique Gaspard-Monge (LIGM), University Paris-Est Marne-la-Vall\u00e9e, B\u00e2timent Copernic - 5, bd Descartes, Champs sur Marne, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padua, via Gradenigo 6B, Padua, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Laboratoire d\u2019Informatique Gaspard-Monge (LIGM), University Paris-Est Marne-la-Vall\u00e9e, B\u00e2timent Copernic - 5, bd Descartes, Champs sur Marne, France","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I4210154111"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067815810","display_name":"Matteo Comin","orcid":"https://orcid.org/0000-0001-8545-4359"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Matteo Comin","raw_affiliation_strings":["Department of Information Engineering, University of Padua, via Gradenigo 6B, Padua, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padua, via Gradenigo 6B, Padua, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067815810"],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":0.5806,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76410669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"17","issue":"05","first_page":"1940011","last_page":"1940011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9986000061035156,"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":0.9901000261306763,"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":0.7065638899803162},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6559539437294006},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5928184986114502},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.5576893091201782},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5323230624198914},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5172470211982727},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5007266998291016},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4946281611919403},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.45205092430114746},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42409053444862366},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3382423222064972},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3291322588920593},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29322439432144165},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.2560802102088928},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11473530530929565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7065638899803162},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6559539437294006},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5928184986114502},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.5576893091201782},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5323230624198914},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5172470211982727},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5007266998291016},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4946281611919403},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.45205092430114746},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42409053444862366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3382423222064972},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3291322588920593},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29322439432144165},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2560802102088928},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11473530530929565},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"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":"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":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","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":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060005","descriptor_name":"Genotyping Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060005","descriptor_name":"Genotyping Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060005","descriptor_name":"Genotyping Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1142/s0219720019400110","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720019400110","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:31856669","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31856669","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":"Journal of bioinformatics and computational biology","raw_type":null},{"id":"pmh:oai:HAL:hal-04488234v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04488234","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Bioinformatics and Computational Biology, 2019, 17 (05), pp.1940011. &#x27E8;10.1142/S0219720019400110&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:www.research.unipd.it:11577/3331160","is_oa":false,"landing_page_url":"http://hdl.handle.net/11577/3331160","pdf_url":null,"source":{"id":"https://openalex.org/S4377196283","display_name":"Research Padua  Archive (University of Padua)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W115447291","https://openalex.org/W1931027898","https://openalex.org/W2020255088","https://openalex.org/W2057253402","https://openalex.org/W2069066547","https://openalex.org/W2092880969","https://openalex.org/W2096128575","https://openalex.org/W2096791516","https://openalex.org/W2103441770","https://openalex.org/W2109153336","https://openalex.org/W2121016876","https://openalex.org/W2122732537","https://openalex.org/W2125557405","https://openalex.org/W2142167651","https://openalex.org/W2143423077","https://openalex.org/W2147733682","https://openalex.org/W2158322625","https://openalex.org/W2159647614","https://openalex.org/W2296597603","https://openalex.org/W2438121987","https://openalex.org/W2463091895","https://openalex.org/W2466892528","https://openalex.org/W2515342656","https://openalex.org/W2561001142","https://openalex.org/W2591953849","https://openalex.org/W2799170772","https://openalex.org/W2810099320","https://openalex.org/W2902947058","https://openalex.org/W2991421430","https://openalex.org/W3098304617","https://openalex.org/W4247053599"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W4237510188","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"Many":[0],"bioinformatics":[1],"tools":[2],"heavily":[3],"rely":[4],"on":[5],"[Formula:":[6,26,43,77,137],"see":[7,27,44,78,138],"text]-mer":[8,28],"dictionaries":[9,29],"to":[10,40,66,83,109,116,155],"describe":[11],"the":[12,52,84,94,101,118,125,157],"composition":[13],"of":[14,37,54,75,86,93,96,120,135,159],"sequences":[15],"and":[16,80,104,144,153],"allow":[17],"for":[18,57,127],"faster":[19],"reference-free":[20],"algorithms":[21],"or":[22],"look-ups.":[23],"Unfortunately,":[24],"naive":[25],"are":[30,107],"very":[31,34],"memory-inefficient,":[32],"requiring":[33],"large":[35],"amount":[36],"storage":[38],"space":[39,152],"save":[41],"each":[42],"text]-mer.":[45],"This":[46],"problem":[47],"is":[48,165],"generally":[49],"worsened":[50],"by":[51],"necessity":[53],"an":[55,68,114],"index":[56],"fast":[58],"queries.":[59],"In":[60],"this":[61],"work,":[62],"we":[63,112],"discuss":[64],"how":[65,132],"build":[67],"indexed":[69,149],"linear":[70,151],"reference":[71],"containing":[72],"a":[73,133],"set":[74],"input":[76],"text]-mers":[79],"its":[81],"application":[82,115],"compression":[85,158],"quality":[87,102,121,160],"scores":[88],"in":[89,100,150],"FASTQ":[90],"files.":[91],"Most":[92],"entropies":[95],"sequencing":[97],"data":[98],"lie":[99],"scores,":[103],"thus":[105],"they":[106],"difficult":[108],"compress.":[110],"Here,":[111],"present":[113],"improve":[117,156],"compressibility":[119],"values":[122],"while":[123],"preserving":[124],"information":[126],"SNP":[128,142],"calling.":[129],"We":[130],"show":[131],"dictionary":[134],"significant":[136],"text]-mers,":[139],"obtained":[140],"from":[141],"databases":[143],"multiple":[145],"genomes,":[146],"can":[147],"be":[148],"used":[154],"value.":[161],"Availability:":[162],"The":[163],"software":[164],"freely":[166],"available":[167],"at":[168],"https://github.com/yhhshb/yalff":[169],".":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}
