{"id":"https://openalex.org/W2770939534","doi":"https://doi.org/10.1093/bioinformatics/btx737","title":"CALQ: compression of quality values of aligned sequencing data","display_name":"CALQ: compression of quality values of aligned sequencing data","publication_year":2017,"publication_date":"2017-11-22","ids":{"openalex":"https://openalex.org/W2770939534","doi":"https://doi.org/10.1093/bioinformatics/btx737","mag":"2770939534","pmid":"https://pubmed.ncbi.nlm.nih.gov/29186284"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx737","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx737","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/10/1650/25118186/btx737.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/34/10/1650/25118186/btx737.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036024697","display_name":"Jan Voges","orcid":"https://orcid.org/0000-0002-6080-660X"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210088543","display_name":"Institut f\u00fcr Informationsverarbeitung","ror":"https://ror.org/0047j9t38","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210088543"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jan Voges","raw_affiliation_strings":["Fakult\u00e4t f\u00fcr Elektrotechnik und Informatik, Institut f\u00fcr Informationsverarbeitung (TNT), Leibniz Universit\u00e4t Hannover, Hannover, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6080-660X","affiliations":[{"raw_affiliation_string":"Fakult\u00e4t f\u00fcr Elektrotechnik und Informatik, Institut f\u00fcr Informationsverarbeitung (TNT), Leibniz Universit\u00e4t Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I4210088543","https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064913233","display_name":"J\u00f6rn \u00d6stermann","orcid":"https://orcid.org/0000-0002-6743-3324"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210088543","display_name":"Institut f\u00fcr Informationsverarbeitung","ror":"https://ror.org/0047j9t38","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210088543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00f6rn Ostermann","raw_affiliation_strings":["Fakult\u00e4t f\u00fcr Elektrotechnik und Informatik, Institut f\u00fcr Informationsverarbeitung (TNT), Leibniz Universit\u00e4t Hannover, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fakult\u00e4t f\u00fcr Elektrotechnik und Informatik, Institut f\u00fcr Informationsverarbeitung (TNT), Leibniz Universit\u00e4t Hannover, Hannover, Germany","institution_ids":["https://openalex.org/I4210088543","https://openalex.org/I114112103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044149683","display_name":"Mikel Hern\u00e1ez","orcid":"https://orcid.org/0000-0003-0443-2305"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mikel Hernaez","raw_affiliation_strings":["Carl R. Woese Institute for Genomic Biology, University of Illinois, Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carl R. Woese Institute for Genomic Biology, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036024697","https://openalex.org/A5044149683"],"corresponding_institution_ids":["https://openalex.org/I114112103","https://openalex.org/I157725225","https://openalex.org/I4210088543"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.6849,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.92553451,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"34","issue":"10","first_page":"1650","last_page":"1658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.6614999771118164,"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":0.6614999771118164,"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":0.21240000426769257,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.5717254877090454},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5659232139587402},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5360178351402283},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.470468133687973},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42743080854415894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.195363849401474},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07244646549224854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5717254877090454},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5659232139587402},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5360178351402283},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.470468133687973},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42743080854415894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.195363849401474},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07244646549224854},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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":"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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":"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":"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}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btx737","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx737","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/10/1650/25118186/btx737.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:29186284","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29186284","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:europepmc.org:5490461","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5946873","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx737","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx737","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/10/1650/25118186/btx737.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":[{"score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4131991648","display_name":null,"funder_award_id":"U01 CA198943","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G7243717575","display_name":null,"funder_award_id":"1 U01 CA198943-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8675792435","display_name":null,"funder_award_id":"U01 CA198943","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2770939534.pdf","grobid_xml":"https://content.openalex.org/works/W2770939534.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W657799361","https://openalex.org/W2025648894","https://openalex.org/W2042947822","https://openalex.org/W2058087601","https://openalex.org/W2060965924","https://openalex.org/W2069066547","https://openalex.org/W2104846587","https://openalex.org/W2108234281","https://openalex.org/W2109153336","https://openalex.org/W2117608012","https://openalex.org/W2119180969","https://openalex.org/W2119923823","https://openalex.org/W2124985265","https://openalex.org/W2125557405","https://openalex.org/W2129652681","https://openalex.org/W2135216100","https://openalex.org/W2138196010","https://openalex.org/W2147733682","https://openalex.org/W2149434098","https://openalex.org/W2159084616","https://openalex.org/W2168133698","https://openalex.org/W2170551349","https://openalex.org/W2296597603","https://openalex.org/W2516970777","https://openalex.org/W2538355508","https://openalex.org/W2562306914","https://openalex.org/W2567256921","https://openalex.org/W2952969776","https://openalex.org/W3098304617","https://openalex.org/W6697520301"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"Motivation:":[0],"Recent":[1],"advancements":[2],"in":[3,30,110,199,219],"high-throughput":[4],"sequencing":[5,137],"technology":[6],"have":[7,20],"led":[8],"to":[9,43,178],"a":[10,67,83,132,154,167],"rapid":[11],"growth":[12],"of":[13,26,33,55,58,78,91,103,112,139,170,174,201,209],"genomic":[14],"data.":[15],"Several":[16],"lossless":[17,181],"compression":[18,70],"schemes":[19],"been":[21],"proposed":[22],"for":[23,52,107,207],"the":[24,31,56,62,76,89,92,101,115,125,140,162,179,195,210],"coding":[25],"such":[27],"data":[28,138,164,235],"present":[29,66],"form":[32],"raw":[34],"FASTQ":[35],"files":[36],"and":[37,124,127,146,205,214,222],"aligned":[38],"SAM/BAM":[39],"files.":[40,60],"However,":[41],"due":[42],"their":[44],"high":[45],"entropy,":[46],"losslessly":[47],"compressed":[48,59,117],"quality":[49,63,79,108,122,148],"values":[50,109,149],"account":[51],"about":[53,171],"80%":[54],"size":[57,118,168],"For":[61],"values,":[64],"we":[65,87,152,184],"novel":[68],"lossy":[69,105,197],"scheme":[71],"named":[72],"CALQ.":[73],"By":[74,144],"controlling":[75],"coarseness":[77],"value":[80],"quantization":[81],"with":[82,150,161,176],"statistical":[84],"genotyping":[85],"model,":[86],"minimize":[88],"impact":[90],"introduced":[93],"distortion":[94],"on":[95],"downstream":[96],"analyses.":[97],"Results:":[98],"We":[99],"analyze":[100],"performance":[102,159],"several":[104],"compressors":[106,198],"terms":[111,200],"trade-off":[113],"between":[114],"achieved":[116,129],"(in":[119],"bits":[120],"per":[121],"value)":[123],"Precision":[126,206],"Recall":[128,204],"after":[130],"running":[131],"variant":[133,157,202],"calling":[134,158,203],"pipeline":[135],"over":[136],"well-known":[141],"NA12878":[142],"individual.":[143],"compressing":[145],"reconstructing":[147],"CALQ,":[151],"observe":[153],"better":[155,193],"average":[156],"than":[160,194],"original":[163],"while":[165],"achieving":[166],"reduction":[169],"one":[172],"order":[173],"magnitude":[175],"respect":[177],"state-of-the-art":[180,196],"compressors.":[182],"Furthermore,":[183],"show":[185],"that":[186],"CALQ":[187,216],"performs":[188],"as":[189,191],"good":[190],"or":[192,230],"most":[208],"analyzed":[211],"datasets.":[212],"Availability":[213],"implementation:":[215],"is":[217],"written":[218],"C":[220],"++":[221],"can":[223],"be":[224],"downloaded":[225],"from":[226],"https://github.com/voges/calq.":[227],"Contact:":[228],"voges@tnt.uni-hannover.de":[229],"mhernaez@illinois.edu.":[231],"Supplementary":[232,234],"information:":[233],"are":[236],"available":[237],"at":[238],"Bioinformatics":[239],"online.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}