{"id":"https://openalex.org/W2149434098","doi":"https://doi.org/10.1142/s0219720014420025","title":"Aligned genomic data compression via improved modeling","display_name":"Aligned genomic data compression via improved modeling","publication_year":2014,"publication_date":"2014-10-08","ids":{"openalex":"https://openalex.org/W2149434098","doi":"https://doi.org/10.1142/s0219720014420025","mag":"2149434098","pmid":"https://pubmed.ncbi.nlm.nih.gov/25395305"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720014420025","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720014420025","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/A5045294377","display_name":"Idoia Ochoa","orcid":"https://orcid.org/0000-0003-1864-7868"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Idoia Ochoa","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, 350 Serra Mall, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, 350 Serra Mall, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044149683","display_name":"Mikel Hern\u00e1ez","orcid":"https://orcid.org/0000-0003-0443-2305"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mikel Hernaez","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, 350 Serra Mall, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, 350 Serra Mall, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043344688","display_name":"Tsachy Weissman","orcid":"https://orcid.org/0009-0008-1099-691X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsachy Weissman","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, 350 Serra Mall, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, 350 Serra Mall, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045294377"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.6974,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88254664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"12","issue":"06","first_page":"1442002","last_page":"1442002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9782999753952026,"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":0.6748719215393066},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6168540120124817},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5606471300125122},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.518701434135437},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.4879126250743866},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.47725316882133484},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.4544847011566162},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2520259618759155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.195513516664505},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14510658383369446},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.14469894766807556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6748719215393066},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6168540120124817},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5606471300125122},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.518701434135437},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.4879126250743866},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.47725316882133484},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.4544847011566162},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2520259618759155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.195513516664505},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14510658383369446},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.14469894766807556},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","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":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1142/s0219720014420025","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720014420025","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:25395305","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25395305","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:europepmc.org:4586787","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5666573","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":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321705","display_name":"Eusko Jaurlaritza","ror":"https://ror.org/00pz2fp31"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1588594383","https://openalex.org/W2005112508","https://openalex.org/W2020255088","https://openalex.org/W2050374641","https://openalex.org/W2085522429","https://openalex.org/W2092880969","https://openalex.org/W2108234281","https://openalex.org/W2109153336","https://openalex.org/W2159084616","https://openalex.org/W2166588423","https://openalex.org/W2167943254","https://openalex.org/W2170551349","https://openalex.org/W4298335083"],"related_works":["https://openalex.org/W4383723869","https://openalex.org/W3007688875","https://openalex.org/W4384298135","https://openalex.org/W2768628697","https://openalex.org/W2388481516","https://openalex.org/W2161302774","https://openalex.org/W2011090518","https://openalex.org/W3080614128","https://openalex.org/W2103127675","https://openalex.org/W2945049259"],"abstract_inverted_index":{"With":[0],"the":[1,4,10,15,19,39,48,92,98,109,118,125,135,139,159,167,180,228,237],"release":[2],"of":[3,17,22,41,44,57,72,78,94,124,134,141,200],"latest":[5],"Next-Generation":[6],"Sequencing":[7],"(NGS)":[8],"machine,":[9],"HiSeq":[11],"X":[12],"by":[13,152,172,189,226,240],"Illumina,":[14],"cost":[16],"sequencing":[18,36,43,205],"whole":[20],"genome":[21],"a":[23,30,231],"human":[24],"is":[25,224],"expected":[26],"to":[27,29,50,87,90,102,234],"drop":[28],"mere":[31],"$1000.":[32],"This":[33],"milestone":[34],"in":[35,108,230,236],"history":[37],"marks":[38],"era":[40],"affordable":[42],"individuals":[45],"and":[46,95,122,186,191,196,202],"opens":[47],"doors":[49],"personalized":[51],"medicine.":[52],"In":[53],"accord,":[54],"unprecedented":[55],"volumes":[56],"genomic":[58],"data":[59,142,155,229],"will":[60,66],"require":[61],"storage":[62],"for":[63,144,158,183,214],"processing.":[64],"There":[65],"be":[67,84],"dire":[68],"need":[69],"not":[70,129,212],"only":[71],"compressing":[73,145],"aligned":[74,146,160,217],"data,":[75,161,206],"but":[76],"also":[77],"generating":[79],"compressed":[80,238],"files":[81],"that":[82,179],"can":[83,163],"fed":[85],"directly":[86],"downstream":[88,241],"applications":[89],"facilitate":[91],"analysis":[93],"inference":[96],"on":[97,117,131],"data.":[99,136,218],"Several":[100],"approaches":[101],"this":[103],"challenge":[104],"have":[105],"been":[106,116],"proposed":[107,174],"literature;":[110],"however,":[111],"focus":[112],"thus":[113],"far":[114],"has":[115],"low":[119],"coverage":[120,216],"regime":[121],"most":[123],"suggested":[126],"compressors":[127],"are":[128],"based":[130],"effective":[132],"modeling":[133,143],"We":[137],"demonstrate":[138],"benefit":[140],"reads.":[147],"Specifically,":[148],"we":[149,162],"show":[150],"that,":[151],"working":[153],"with":[154],"models":[156],"designed":[157],"improve":[164],"considerably":[165],"over":[166],"best":[168],"compression":[169,184,222],"ratio":[170,223],"achieved":[171,225],"previously":[173],"algorithms.":[175],"Our":[176],"results":[177],"indicate":[178],"pareto-optimal":[181],"barrier":[182],"rate":[185],"speed":[187],"claimed":[188],"Bonfield":[190],"Mahoney":[192],"(2013)":[193],"[Bonfield":[194],"JK":[195],"Mahoneys":[197],"MV,":[198],"Compression":[199],"FASTQ":[201],"SAM":[203],"format":[204],"PLOS":[207],"ONE,":[208],"8(3):e59190,":[209],"2013.]":[210],"does":[211],"apply":[213],"high":[215],"Furthermore,":[219],"our":[220],"improved":[221],"splitting":[227],"manner":[232],"conducive":[233],"operations":[235],"domain":[239],"applications.":[242]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}