{"id":"https://openalex.org/W3132214945","doi":"https://doi.org/10.1093/bioinformatics/btab102","title":"Genozip: a universal extensible genomic data compressor","display_name":"Genozip: a universal extensible genomic data compressor","publication_year":2021,"publication_date":"2021-02-12","ids":{"openalex":"https://openalex.org/W3132214945","doi":"https://doi.org/10.1093/bioinformatics/btab102","mag":"3132214945","pmid":"https://pubmed.ncbi.nlm.nih.gov/33585897"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab102","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab102","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/16/2225/39950322/btab102.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","license_id":"https://openalex.org/licenses/cc-by","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/37/16/2225/39950322/btab102.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047170593","display_name":"Divon Lan","orcid":"https://orcid.org/0000-0002-9794-6825"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Divon Lan","raw_affiliation_strings":["Australian Centre for Ancient DNA, School of Biological Sciences, The Environment Institute, Faculty of Sciences, The University of Adelaide , Adelaide, SA 5005, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9794-6825","affiliations":[{"raw_affiliation_string":"Australian Centre for Ancient DNA, School of Biological Sciences, The Environment Institute, Faculty of Sciences, The University of Adelaide , Adelaide, SA 5005, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048618496","display_name":"Raymond Tobler","orcid":"https://orcid.org/0000-0002-4603-1473"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ray Tobler","raw_affiliation_strings":["Australian Centre for Ancient DNA, School of Biological Sciences, The Environment Institute, Faculty of Sciences, The University of Adelaide , Adelaide, SA 5005, Australia","Centre of Excellence for Australian Biodiversity and Heritage (CABAH), School of Biological Sciences, University of Adelaide , Adelaide, SA 5005, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4603-1473","affiliations":[{"raw_affiliation_string":"Australian Centre for Ancient DNA, School of Biological Sciences, The Environment Institute, Faculty of Sciences, The University of Adelaide , Adelaide, SA 5005, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"Centre of Excellence for Australian Biodiversity and Heritage (CABAH), School of Biological Sciences, University of Adelaide , Adelaide, SA 5005, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059118201","display_name":"Yassine Souilmi","orcid":"https://orcid.org/0000-0001-7543-4864"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yassine Souilmi","raw_affiliation_strings":["Australian Centre for Ancient DNA, School of Biological Sciences, The Environment Institute, Faculty of Sciences, The University of Adelaide , Adelaide, SA 5005, Australia","National Centre for Indigenous Genomics, Australian National University , Canberra, ACT 0200, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Centre for Ancient DNA, School of Biological Sciences, The Environment Institute, Faculty of Sciences, The University of Adelaide , Adelaide, SA 5005, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"National Centre for Indigenous Genomics, Australian National University , Canberra, ACT 0200, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082962342","display_name":"Bastien Llamas","orcid":"https://orcid.org/0000-0002-5550-9176"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Bastien Llamas","raw_affiliation_strings":["Australian Centre for Ancient DNA, School of Biological Sciences, The Environment Institute, Faculty of Sciences, The University of Adelaide , Adelaide, SA 5005, Australia","Centre of Excellence for Australian Biodiversity and Heritage (CABAH), School of Biological Sciences, University of Adelaide , Adelaide, SA 5005, Australia","National Centre for Indigenous Genomics, Australian National University , Canberra, ACT 0200, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5550-9176","affiliations":[{"raw_affiliation_string":"Australian Centre for Ancient DNA, School of Biological Sciences, The Environment Institute, Faculty of Sciences, The University of Adelaide , Adelaide, SA 5005, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"Centre of Excellence for Australian Biodiversity and Heritage (CABAH), School of Biological Sciences, University of Adelaide , Adelaide, SA 5005, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"National Centre for Indigenous Genomics, Australian National University , Canberra, ACT 0200, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047170593","https://openalex.org/A5059118201","https://openalex.org/A5082962342"],"corresponding_institution_ids":["https://openalex.org/I118347636","https://openalex.org/I5681781"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":5.4567,"has_fulltext":true,"cited_by_count":55,"citation_normalized_percentile":{"value":0.96386048,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"37","issue":"16","first_page":"2225","last_page":"2230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8313000202178955,"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":0.8313000202178955,"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":0.0430000014603138,"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":0.020800000056624413,"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":0.8415893316268921},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.6713476777076721},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5895940661430359},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5653636455535889},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5279048085212708},{"id":"https://openalex.org/keywords/file-size","display_name":"File size","score":0.5062834024429321},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.4585942327976227},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4110185205936432},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34010303020477295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.099945068359375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415893316268921},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.6713476777076721},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5895940661430359},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5653636455535889},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5279048085212708},{"id":"https://openalex.org/C2776029614","wikidata":"https://www.wikidata.org/wiki/Q1146367","display_name":"File size","level":2,"score":0.5062834024429321},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.4585942327976227},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4110185205936432},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34010303020477295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.099945068359375}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btab102","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab102","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/16/2225/39950322/btab102.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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33585897","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33585897","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:digital.library.adelaide.edu.au:2440/132569","is_oa":true,"landing_page_url":"https://hdl.handle.net/2440/132569","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"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":"http://dx.doi.org/10.1093/bioinformatics/btab102","raw_type":"Journal article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8388020","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8388020","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btab102","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab102","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/16/2225/39950322/btab102.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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G6790371072","display_name":null,"funder_award_id":"ARC DP190103705","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132214945.pdf","grobid_xml":"https://content.openalex.org/works/W3132214945.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2108234281","https://openalex.org/W2135216100","https://openalex.org/W2142386149","https://openalex.org/W2905575949","https://openalex.org/W2949113050","https://openalex.org/W3024135825"],"related_works":["https://openalex.org/W2170479371","https://openalex.org/W4313450465","https://openalex.org/W2154495965","https://openalex.org/W4367668844","https://openalex.org/W2334348803","https://openalex.org/W2573024996","https://openalex.org/W2769887238","https://openalex.org/W1622142713","https://openalex.org/W2175326011","https://openalex.org/W3132214945"],"abstract_inverted_index":{"We":[0,143],"present":[1],"Genozip,":[2],"a":[3,18,22,95,115,202],"universal":[4],"and":[5,21,45,66,77,104,152,180,200,213],"fully":[6],"featured":[7],"compression":[8,27,41,50,81,117,123],"software":[9,20],"for":[10,25,34,51,111,124,133,188],"genomic":[11,26,37,53],"data.":[12],"Genozip":[13,47,74,91,99,112,171,207],"is":[14,75,92,172,178,186,192,208],"designed":[15],"to":[16,113],"be":[17,114],"general-purpose":[19,116],"development":[23],"framework":[24],"by":[28,157],"providing":[29],"five":[30],"core":[31],"capabilities-universality":[32],"(support":[33],"all":[35],"common":[36],"file":[38,126],"formats),":[39],"high":[40],"ratios,":[42,82],"speed,":[43],"feature-richness":[44],"extensibility.":[46],"delivers":[48],"high-performance":[49],"widelyused":[52],"data":[54,134,218],"formats":[55],"in":[56,140,165,174],"genomics":[57],"research,":[58],"namely":[59],"FASTQ,":[60],"SAM/BAM/CRAM,":[61],"VCF,":[62],"GVF,":[63],"FASTA,":[64],"PHYLIP":[65],"23andMe":[67],"formats.":[68],"Our":[69],"test":[70],"results":[71],"show":[72],"that":[73,145],"fast":[76],"achieves":[78],"greatly":[79],"improved":[80],"even":[83],"when":[84],"the":[85,98,141,150,158,195],"files":[86],"are":[87,219],"already":[88],"compressed.":[89],"Further,":[90],"architected":[93],"with":[94],"separation":[96],"of":[97,154],"Framework":[100],"from":[101],"file-format-specific":[102],"Segmenters":[103],"data-type-specific":[105],"Codecs.":[106],"With":[107],"this,":[108],"we":[109],"intend":[110],"platform":[118],"where":[119],"researchers":[120],"can":[121],"implement":[122],"additional":[125],"formats,":[127],"as":[128,130,201],"well":[129],"new":[131],"codecs":[132],"types":[135],"or":[136],"fields":[137],"within":[138],"files,":[139],"future.":[142],"anticipate":[144],"this":[146,166],"will":[147],"ultimately":[148],"increase":[149],"visibility":[151],"adoption":[153],"these":[155],"algorithms":[156],"user":[159],"community,":[160],"thereby":[161],"accelerating":[162],"further":[163],"innovation":[164],"space.":[167],"AVAILABILITY":[168],"AND":[169],"IMPLEMENTATION:":[170],"written":[173],"C.":[175],"The":[176,184],"code":[177],"open-source":[179],"available":[181,220],"on":[182,205,210],"http://www.genozip.com.":[183],"package":[185,197],"free":[187],"non-commercial":[189],"use.":[190],"It":[191],"distributed":[193],"through":[194],"Conda":[196],"manager,":[198],"github,":[199],"Docker":[203],"container":[204],"DockerHub.":[206],"tested":[209],"Linux,":[211],"Mac":[212],"Windows.":[214],"SUPPLEMENTARY":[215],"INFORMATION:":[216],"Supplementary":[217],"at":[221],"Bioinformatics":[222],"online.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
