{"id":"https://openalex.org/W2097749295","doi":"https://doi.org/10.1109/itw.2012.6404708","title":"Reference based genome compression","display_name":"Reference based genome compression","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2097749295","doi":"https://doi.org/10.1109/itw.2012.6404708","mag":"2097749295"},"language":"en","primary_location":{"id":"doi:10.1109/itw.2012.6404708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw.2012.6404708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Information Theory Workshop","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1204.1912","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051670362","display_name":"Bobbie Chern","orcid":null},"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":"B. G. Chern","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA","[Department of Electrical Engineering, Stanford University, CA, 94305, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Electrical Engineering, Stanford University, CA, 94305, USA]","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","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":false,"raw_author_name":"I. Ochoa","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA","[Department of Electrical Engineering, Stanford University, CA, 94305, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Electrical Engineering, Stanford University, CA, 94305, USA]","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024618330","display_name":"Alexandros Manolakos","orcid":"https://orcid.org/0000-0002-1014-8426"},"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":"A. Manolakos","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA","[Department of Electrical Engineering, Stanford University, CA, 94305, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Electrical Engineering, Stanford University, CA, 94305, USA]","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049196468","display_name":"Albert No","orcid":"https://orcid.org/0000-0002-6346-4182"},"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":"A. No","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA","[Department of Electrical Engineering, Stanford University, CA, 94305, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Electrical Engineering, Stanford University, CA, 94305, USA]","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066970557","display_name":"Kartik Venkat","orcid":"https://orcid.org/0000-0002-7902-9724"},"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":"K. Venkat","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA","[Department of Electrical Engineering, Stanford University, CA, 94305, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Electrical Engineering, Stanford University, CA, 94305, 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":"T. Weissman","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA","[Department of Electrical Engineering, Stanford University, CA, 94305, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Electrical Engineering, Stanford University, CA, 94305, USA]","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5051670362"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":3.537,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92997635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"427","last_page":"431"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9975000023841858,"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/T11247","display_name":"Plant nutrient uptake and metabolism","score":0.9797999858856201,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7364970445632935},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.7217016220092773},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6787928938865662},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6657435894012451},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6568337082862854},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.5164982676506042},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4807055592536926},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4791392982006073},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4351620674133301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2653047740459442},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.17880138754844666},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12208208441734314},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11393818259239197},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0841444730758667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7364970445632935},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.7217016220092773},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6787928938865662},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6657435894012451},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6568337082862854},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5164982676506042},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4807055592536926},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4791392982006073},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4351620674133301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2653047740459442},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.17880138754844666},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12208208441734314},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11393818259239197},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0841444730758667},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/itw.2012.6404708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw.2012.6404708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Information Theory Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1204.1912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1204.1912","pdf_url":"https://arxiv.org/pdf/1204.1912","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.348.4526","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.4526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stanford.edu/%7Eamanolak/dna2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.749.5843","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.749.5843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1204.1912.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1204.1912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1204.1912","pdf_url":"https://arxiv.org/pdf/1204.1912","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W153132339","https://openalex.org/W788498898","https://openalex.org/W2000466469","https://openalex.org/W2001725958","https://openalex.org/W2008459483","https://openalex.org/W2024975965","https://openalex.org/W2051929999","https://openalex.org/W2060108852","https://openalex.org/W2072285646","https://openalex.org/W2101931396","https://openalex.org/W2107745473","https://openalex.org/W2112509895","https://openalex.org/W2113649367","https://openalex.org/W2115613939","https://openalex.org/W2130419122","https://openalex.org/W2137661542","https://openalex.org/W2142003566","https://openalex.org/W2146026812","https://openalex.org/W2155471967","https://openalex.org/W2159084616","https://openalex.org/W2163294786","https://openalex.org/W2168909179","https://openalex.org/W6606157611","https://openalex.org/W6679723989","https://openalex.org/W6680051036"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W1973775000","https://openalex.org/W4361984506","https://openalex.org/W2107233609"],"abstract_inverted_index":{"DNA":[0],"sequencing":[1],"technology":[2],"has":[3],"advanced":[4],"to":[5,46,54,74,96,108,116,123],"a":[6,56,60,69,103],"point":[7],"where":[8],"storage":[9],"is":[10],"becoming":[11],"the":[12,16,40,72,75,91,110],"central":[13],"bottleneck":[14],"in":[15],"acquisition":[17],"and":[18,32,78],"mining":[19],"of":[20,25,90],"more":[21],"data.":[22],"Large":[23],"amounts":[24],"data":[26],"are":[27,106],"vital":[28],"for":[29],"genomics":[30],"research,":[31],"generic":[33],"compression":[34],"tools,":[35],"while":[36,119],"viable,":[37],"cannot":[38],"offer":[39],"same":[41],"savings":[42],"as":[43,102],"approaches":[44],"tuned":[45],"inherent":[47],"biological":[48],"properties.":[49],"We":[50],"propose":[51],"an":[52,84,88],"algorithm":[53,66,95],"compress":[55],"target":[57,76],"genome":[58,99,114],"given":[59],"known":[61],"reference":[62,73],"genome.":[63],"The":[64],"proposed":[65],"first":[67],"generates":[68],"mapping":[70,82],"from":[71],"genome,":[77],"then":[79],"compresses":[80,121],"this":[81],"with":[83,100],"entropy":[85],"coder.":[86],"As":[87],"illustration":[89],"performance:":[92],"applying":[93],"our":[94],"James":[97],"Watson's":[98],"hg18":[101],"reference,":[104],"we":[105],"able":[107],"reduce":[109],"2991":[111],"megabyte":[112],"(MB)":[113],"down":[115],"6.99":[117],"MB,":[118],"Gzip":[120],"it":[122],"834.8":[124],"MB.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
